Yuchi Wang, Rongyao Fang, Weihao Yu, Xilin Wei, Tiancheng Gu, Dingkang Yang, Hang Zhang, Dayiheng Liu 等 10 位作者
Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equally essential for applying AI agents to real-world productivity tasks. We study this crucial capability through webpage development, a practical and readily evaluable setting in which existing benchmarks remain largely idealized: they typically focus on reconstructing visual targets or generating webpages from textual instructions alone, overlooking the more common workflow of developing from visual examples. Specifically, we introduce RefCraft, a benchmark comprising 300 realistic multimodal webpage-development tasks that combine natural-language instructions with screenshots from one to five reference webpages. Agents must selectively interpret and utilize these references while rendering, visually inspecting, and iteratively refining their outputs. We evaluate the resulting open-ended artifacts using independently verifiable keypoints and complementary programmatic and VLM judges. Across nine frontier (M)LLMs, the strongest system achieves an overall score of only 52.12 out of 100, revealing that visual-reference-conditioned agentic generation remains a substantial challenge for current models in practical webpage-development settings.
Zhiyong Zhou, Sheng Liao, Youshen Xiao, Xiaolin Li, Yakang Dai
EEG extended-source imaging aims to localize active cortical regions and characterize their spatial extent, yet supervised inverse networks typically depend on synthetic EEG-source pairs and may be sensitive to synthetic-to-real mismatch. We propose a physics-informed self-supervised implicit neural representation (INR) framework for spatial source reconstruction without paired source labels or simulation-based supervised pretraining. The lead field matrix encodes the source-to-sensor volume-conduction model and constrains the INR through agreement between predicted and measured EEG. Cortical current density is modeled as a continuous coordinate-conditioned field. A classical inverse estimate provides warm initialization and spatial constraints on source activity, while patch-integrated projection maps the field to discrete source coefficients for forward modeling. Simulations with varying noise levels, source counts, and source extents showed the clearest advantage in identifying active cortical regions, particularly for multiple and larger sources. Quantitative and qualitative evaluations using real EEG recordings from epilepsy patients and intracranial stimulation experiments further supported the feasibility of the framework for source imaging. These findings suggest the potential of physics-informed self-supervised INR for extended-source imaging.
Ximo Zhu, Ruiqi Liu, Yi Han, Zhengan Wu, Gengsheng Li, ZiAn Wang, Zhu Yuantian, Jin Jiang 等 9 位作者
Proprietary language models exhibit strong reasoning and coding capabilities, but their output distributions are inaccessible, making fine-grained distillation methods that rely on teacher logits difficult to apply directly to black-box models. We observe that rich textual feedback from a black-box teacher can be treated as privileged information (PI) and converted, through a PI-conditioned privileged teacher, into dense supervision signals on the student's own trajectories. However, what PI should be acquired from the teacher to most effectively support student learning remains unclear. PI strategies that differ in where they focus, what information they request, and how much detail they provide can have substantially different effects on the current student, and their relative effectiveness can further change as training progresses. Based on this observation, we propose Evolving Privileged Information Strategies for Black-Box On-Policy Distillation (EvoOPD), which treats PI acquisition itself as an optimization problem and maintains a PI Strategy Bank that evolves with the student state. EvoOPD uses the measured repair utility of PI on the current student to adapt the focus, information type, and granularity of teacher feedback, allowing the acquired information to continually match the student's learning needs. We systematically evaluate EvoOPD on mathematical reasoning and code generation with Qwen3-1.7B, 4B, and 8B students. EvoOPD achieves the best overall performance in all six model-task settings, improving over the strongest baseline in each setting by an average of 2.14 percentage points in mathematics and 1.30 points in code. Further analysis shows that the relative effectiveness of PI acquisition strategies changes with student state, making a fixed strategy difficult to sustain as the best choice throughout distillation.
Jiajun Liang, Yucheng Liao, Yukang Cao, Jiazhe Wei, Ken Li, Wende Tan, Jiankun Zhang, ZY Cui 等 15 位作者
Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation still relies predominantly on discrete tokens. Existing continuous language models either inherit embedding spaces not designed for joint generation and decoding, or compress autoencoded latents to ease diffusion, sacrificing token-level fidelity. Instead of simplifying the representation to suit the generative model, we preserve a high-capacity, decodable text latent and design the diffusion model to learn its distribution directly. We introduce AURORA-LM, a continuous-latent diffusion language model that separates the construction of a decodable text representation from the modeling of its distribution. A Query-based Encoder-Decoder organizes text into a high-capacity, prefix-aligned latent sequence, and a Block-causal Diffusion Transformer learns its distribution through flow matching, generating blocks left to right while denoising positions within each block in parallel. Because such a latent is harder for diffusion to model, AURORA-LM restricts only the noisy-input pathway while retaining the full clean-latent prediction target, accommodating full-width latents without reducing decoder-facing capacity. We further calibrate the noise-level distribution to the latent width, and introduce self-trajectory consistency to bridge independently sampled training noise and iterative denoising at inference. AURORA-LM achieves the strongest performance among evaluated continuous and diffusion-based language models on OpenWebText free generation and XSum summarization. Scaling to 1B parameters with about 1500 EFLOPs of total compute yields further gains, surpassing a larger publicly released latent-diffusion language model under a matched evaluation protocol. All experiments are conducted on Ascend NPUs.
Recycling a target model's own predictions offers a training-free source of proposals for speculative decoding. In vision-language models, however, existing recycling indexes predictions by the last token alone, conflating predictions computed under different images and prefixes; we find that such reuse fails most often at image-sensitive decoding states. Longer keys reduce this aliasing but match fewer states. We introduce \method, which stores target predictions under one-, two-, and three-token keys: contextual memories live only for the current request and are thus implicitly conditioned on its image, while token-level memory persists across requests to retain coverage. At each lookup, entropy-confidence weighting fuses the retrieved predictions according to their key specificity and concentration. Best-first search composes the fused transitions into a candidate tree, supplemented by suffix-matched continuations, and one target pass verifies the tree under greedy decoding. Without training or an auxiliary draft model, \method\ achieves mean speedups over autoregressive decoding of $1.66\speed$ and $1.56\speed$ across seven single-turn benchmarks on Qwen2.5-VL-7B and LLaVA-1.6-7B, exceeding the strongest training-free baseline, Token Recycling ($1.51\speed$ and $1.37\speed$). Our implementation is available in https://github.com/Senmo996/RECAP-official-code.
Zhiheng Li, Zongyang Ma, Jiaxian Chen, Cheng Cui, Yi Liu, Ziqi Zhang, Chunfeng Yuan, Bing Li 等 10 位作者
Optical Character Recognition (OCR) is among the oldest and most widely deployed applications of artificial intelligence. This survey reviews its development, focusing on the Foundation Model Era. We define OCR through faithful transcription: within a specified visual scope, OCR should completely reconstruct the text, notation, and document structure observable in the source image, and every textual, notational, or structural element in the output must be verifiable from visual evidence in that image. We trace the development from specialist OCR models toward unified models, examining joint text detection and recognition, structured sequence generation, and the use of pretrained vision-language models (VLMs). We organize contemporary OCR systems into five coexisting families: modular toolkits and task-specific models, specialized document VLMs, hybrid workflows, general-purpose VLMs, and commercial products and managed services. We compare their architectures, data, and training, examining hallucination and omission, insufficient spatial grounding, and inference cost in generative OCR. We review evaluation from character and scene text recognition to parsing individual structural elements and full-page transcription, highlighting gaps in consistent output definitions, attribution of performance to individual components, and coverage of real capture conditions and visible content and structure. Finally, we summarize the challenges facing OCR and discuss directions for future research. We continuously track related work at https://github.com/zhihengli-casia/Awesome-OCR-in-the-Foundation-Model-Era.
Yulong Li, Rong Xia, Yuxuan Zhang, Jianxu Chen, Xiwei Liu, Haochen Xue, Maosheng Li, Yuhang Liu 等 15 位作者
We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from human populations. DoAtlas-2 integrates 771 research resources covering more than 720,000 participants in 48 countries, from longitudinal clinical phenotypes, medical imaging, and continuous physiological signals to eight molecular layers, together with an evidence network of approximately 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. DoAtlas-2 autonomously formulates research questions from evidence gaps and unresolved mechanisms, prespecifies their causal designs, and generates validated analyses. Supporting, challenging, and unresolved results continuously revise mechanistic interpretations, the causal evidence state, and the discovery frontier, so that DoAtlas-2 self-evolves within a closed loop of hypothesis generation, empirical testing, and renewed discovery. DoAtlas-2 has systematically evaluated 2,031 research questions. In the Human Phenotype Project (HPP), it formulated 4,014 candidate pathway questions across vascular, early-glycemic, and hepatic-metabolic systems, and screening of the first 1,079 yielded statistical support for 756. Representative studies identify blood pressure as a convergence node linking adiposity, hepatic, and lipid phenotypes to vascular outcomes, and show that an adiposity-inflammation-blood-pressure pathway is largely attenuated by joint adjustment for body mass index (BMI) and smoking. The discovered vascular network constitutes a completely interpretable predictive foundation, admitting exact attribution of every prediction and closed-form mediation effects. DoAtlas-2 thereby unifies causal mechanism discovery, population-evidence testing, and interpretable prediction within one continuously evolving foundation.
Frontier language-model agents excel at complex tasks, but high inference costs make transferring their capabilities to smaller models essential. Traditional knowledge distillation achieves this through parameter updates, requiring access to the student's weights and additional training compute while encoding the transferred knowledge implicitly in the parameters. We introduce D-Skill, a framework that treats the teacher as a black box and distills its behavioral advantage into an interpretable natural-language skill by analyzing paired rollouts and identifying behavioral divergences and agreements. The resulting lessons are consolidated offline, with any compatible skill-update backend, into a skill document that is provided to the student at inference time. D-Skill constructs the skill entirely offline from fixed trajectories, without labels, further environment interaction, or weight updates after rollout collection. Across SpreadsheetBench-Verified, ALFWorld, and chess puzzles spanning multiple teacher-student pairs, D-Skill closes 75%-95% of the teacher-student gap without touching model weights. After a single offline pass over the paired traces, D-Skill outperforms one-epoch SFT baselines and remains competitive with multi-epoch SFT. Under the same model family, the resulting student also incurs 5.7x-8.3x lower inference cost per task than the teacher. Our results demonstrate that natural-language skill distillation offers a performant, interpretable, and efficient alternative to weight-based capability transfer.
Yuqing Li, Jiangnan Li, Zheng Lin, Ziyan Zhou, Junjie Wu, Jie Zhou, Mo Yu
Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-based RAG. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning.
Zhijie Zhong, Zhiwen Yu, Kaixiang Yang, Yongheng Liu, Jun Jiang, C. L. Philip Chen
Time series anomaly detection (TSAD) research predominantly focuses on unsupervised architectures to model normal data dynamics under label scarcity. However, practical deployments frequently archive historical operational incidents, questioning whether continuous unsupervised architectural scaling remains the most cost-effective pursuit. In this paper, we empirically quantify the trade-offs between supervisory signals and model complexity. We introduce STAND, a deliberately minimalist supervised baseline based on bidirectional recurrent encoding. Across five benchmark datasets evaluated under a strictly disjoint out-of-sample temporal protocol, minimalist supervised models achieve competitive or superior accuracy relative to complex unsupervised alternatives. Furthermore, controlled label-scaling and few-shot evaluations confirm that these supervisory advantages persist under constrained historical event budgets, while STAND exhibits higher prediction certainty and sharper event delineation than reconstruction-based baselines. These findings encourage the TSAD community to complement algorithmic complexity with data-centric label utilization when annotations are accessible. The source code, benchmark datasets, and an extended Supplementary Document are publicly available at https://emorzz1g.github.io/STAND.
As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the generation process has become a critical challenge. We introduce PGuard, a native, streaming, and plug-in guardrail that transforms safety monitoring from an external serving dependency into an integrated capability of the backbone model. PGuard directly leverages the backbone's intermediate representations for token-level safety detection, without altering its original inference pathway or generation behavior. Specifically, dynamic layer gating selectively aggregates residual-stream representations across layers to extract safety-relevant signals during both prefill and autoregressive decoding. To balance detection accuracy and computational efficiency, PGuard supports multiple representation-modeling architectures, including a lightweight stateless variant and sequence-aware variants built on multi-scale causal EMA-attention and GRU-based recurrent modules. Its design also accounts for the execution characteristics of LLM serving frameworks, such as SGLang, optimizing computation and data access to minimize additional runtime and synchronization overhead. As a result, PGuard incurs only 0.82-2.26% end-to-end overhead on the hundred-billion-parameter backbone Qwen3.5-122B-A10B served by SGLang. Extensive evaluations across more than 30 benchmarks spanning text and multimodal safety, jailbreaks, cyber and CBRN risks, multilingual scenarios, and real-world traffic demonstrate state-of-the-art performance among native guardrails. On text queries with Qwen3.5-9B, PGuard achieves an average F1 score of 0.836, approaching dedicated external guardrails, while supporting deployment-time configuration of category-specific thresholds and enforcement actions.
Xiangyu Li, Jincheng Li, Xing Xie, Bin Guan, Shaohua Kevin Zhou, Rui Yan, Ran Su
Whole-slide multiple instance learning can predict diagnostic and prognostic labels from tissue composition while making limited use of spatial organization. Providing coordinates or a graph does not establish that a trained predictor uses tissue neighborhoods. We examine this gap as spatial blindness and hypothesize that early composition learning can weaken supervision of a spatial pathway. We introduce ResTopoMIL, which freezes a learned composition predictor before training a graph residual with a coordinate-reassignment separation loss. Permutation and information analyses distinguish architectural symmetry, available spatial information and the proposed optimization mechanism. On a controlled spatial task, staged training achieved an AUC of 0.987, compared with 0.684 for the same jointly trained architecture. Performance remained high on a composition-only task. Across four WSI classification and five survival benchmarks, ResTopoMIL improved mean primary performance on eight tasks; four improvements remained significant after Holm-adjusted patient-cluster tests. Coordinate-free residual controls recovered some of the gains, while neighborhood destruction reduced performance close to the composition anchor. Neighborhood-preserving transformations and anatomy-stratified perturbations further characterized this dependence. These results support fixing a composition reference as a practical intervention for learning spatial corrections, while retaining additional appearance capacity as a contributing explanation.
Jing Huang, Yu Cheng, Ziwei Yu, Lan Zhao, Sitan Li, Guangxiu Yao, Xin Wang, Yuanyong Luo 等 14 位作者
Quantization of Large Language Models (LLMs) has become increasingly important for reducing the computational costs and resource requirements for practical deployment. Growing interest in this area has motivated the community to move beyond 8-bit quantization towards 4-bit precision, leading to the development of customized 4-bit formats such as MXFP4 and NVFP4. Recently, HiFloat4 (HiF4) has emerged as a competitive alternative which adopts a Block Floating-Point (BFP) format with a three-level scaling hierarchy, thereby achieving a significantly larger dynamic range. While quantization can substantially reduce memory usage and accelerate inference, it frequently introduces accuracy degradation. Calibration is therefore essential for narrowing the performance gap between low-precision quantized models and their full-precision counterparts. Nevertheless, existing calibration methods are mainly designed and validated using integer-precision formats, such as INT4, lacking support for HiF4 due to its hierarchical BFP structure. In this paper, we investigate three calibration approaches, namely HiGPTQ, HiAutoRound, and HiFlatQuant, to further enhance model quantization based on the HiF4 format. Extensive experiment s demonstrate that all three proposed approaches improve inference accuracy compared with direct HiF4 conversion, reducing the gap between HiF4 and BF16 to less than 1% and outperforming the state-of-the-art NVFP4 format across various models and downstream tasks.
Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large pretrained models. However, standard LoRA typically assigns a fixed rank profile despite layer- and stage-dependent adaptation needs, while recent adaptive-rank variants often rely on heuristic or first-order signals that provide only an indirect link between rank reallocation and local loss behavior. This leaves the rationale behind each rank reallocation insufficiently interpretable. Motivated by this gap, we propose LIRA (Loss-Informed Rank Allocation), a dynamic-rank LoRA method designed to make online rank reallocation more interpretable. LIRA scores each layer by the estimated magnitude of the local loss perturbation associated with its recent LoRA-factor movements under a second-order approximation, making the basis for each rank change interpretable term by term. By periodically applying DELTA (Displacement-Evaluated Loss-Trajectory Allocation), a displacement-based algorithm for LoRA rank reallocation, LIRA produces discrete effective ranks under matched budgets while remaining compatible with standard (A,B) adapters. On RoBERTa-base GLUE under the La-LoRA/LoRA protocol, LIRA outperforms the uniform-LoRA and adaptive-rank baselines reported under this protocol; Trajectory EMA attains performance competitive with Fixed-point Fisher at lower estimation cost.
Long-horizon embodied tasks require agents to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and inefficient integration of heterogeneous memories, limiting their capacity for long-horizon adaptation. To address this, we introduce RoboMemory, a brain-inspired framework that unifies Temporal, Spatial, Semantic, and Episodic memory for efficient long-horizon planning and interactive learning. Its core innovations are a comprehensive memory system designed for embodied tasks, and a dynamic spatial knowledge graph for scalable, consistent memory updates. Extensive experiments on EmbodiedBench show that RoboMemory improves the average success rate of Qwen2.5-VL-72B-Ins by 26.5 percentage points and achieves performance comparable to strong closed-source VLM agents. Real-world trials further suggest RoboMemory's potential for interactive environmental learning by reusing accumulated experience across repeated task attempts. These results demonstrate RoboMemory as a scalable memory-augmented framework for embodied agents, improving long-horizon planning and cumulative learning in complex interactive environments.
Mohammad Kachuee, Phu Mon Htut, Sheng Li, Nikolaos Pappas, Miguel Ballesteros, Yassine Benajiba, Sujith Ravi, Dan Roth
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, substantially expanding their utility while exposing applications to unsafe actions, information leakage, and adversarial manipulation. Multi-agent systems further expand these capabilities through specialization and collaboration, but distributed authority, heterogeneous roles, and opaque or potentially compromised participants make safeguarding even more challenging. Existing defenses address important individual threats but provide fragmented coverage across local execution, system-level interactions, and enforcement mechanisms. We introduce MAS-Guard, a unified framework that closes this gap for safeguarding single- and multi-agent AI applications containing both instrumentable and opaque agents. Within instrumentable agents, the proposed local Agent Guardrail (A-Guard) layer applies task-specific experts to assess agentic events. At the system level, developer-owned Agent Charters and a Control Plane combine deterministic structural checks of routes, agent capabilities, and message formats with semantic assessments of roles and message content. These complementary layers enable enforcement through a shared set of interventions: allow, reflection, confirmation, and block. Evaluated across six benchmarks covering diverse single- and multi-agent scenarios with three agent LLMs from different providers, MAS-Guard reduces the overall attack success rate by 71.5-86.3% relative to unguarded agents, while meeting the utility reference criterion on benign tasks.
Jia Yu, Zilong Wang, Xinyang Jiang, Dongsheng Li, Shuo Wang
Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unvalidated. Existing benchmarks focus on general web or desktop tasks and underrepresent medical software, which requires domain knowledge, exhibits markedly different UI design from mainstream applications, lacks public testing environments, and demands safety validation beyond task completion. We introduce MedCUA-Bench, an interactive benchmark for clinical computer-use agents. It covers 18 clinical scenarios across 10 medical domains, reconstructed from real product manuals and open-source medical systems to capture authentic clinical interfaces while avoiding licensing and privacy constraints. Each task ships with paired intent- and step-level goals to disentangle clinical reasoning from UI execution, and is evaluated by a deterministic checker over task completion and five clinical safety dimensions. Across 23 agents, the best closed-source model reaches 54.2% strict success, while all models remain below 9% on the real OpenEMR. Open-source agents average only 2.5%, with the best reaching 16.2%. MedCUA-Bench exposes the gap between current agents and reliable clinical software use, providing a reproducible testbed for future research.
LaBraM, an early EEG foundation model, demonstrated that large-scale EEG pretraining can yield strong representations for diverse downstream tasks. Building on this foundation, we expand pretraining data and model capacity while retaining its core encoder and objective. We train ten encoders with 5.8 million to 1.97 billion parameters on three EEG collections spanning 25,067 to 79,910 hours, adapting signal preparation and training to heterogeneous recordings. Across 23 tasks, Atom-L* reaches 59.05% mean balanced accuracy at its best evaluated full fine-tuning (Full-FT) checkpoint, 3.61 percentage points above the strongest baseline EEG foundation model. Quark-G leads linear probing (LP) at 54.33%, a 1.24-point margin. Both also lead average task rank. At the last evaluated checkpoints, larger encoders improve Full-FT more consistently than LP, and stronger LP does not guarantee stronger Full-FT. Preserving patch structure improves LP over average pooling. Data-fraction experiments suggest capacity-dependent saturation, while checkpoint trajectories show that downstream performance can decline as pretraining loss falls. Joint classification with a shared Qwen3 readout reaches 50.50% with Molecule-H and Qwen3-8B; increasing language-model size provides no consistent gain. These results demonstrate the value of scaling LaBraM and the importance of matching pretraining scale to downstream adaptation.
Zhicheng He, Xiaohan Xing, Hongqiu Wang, Kun Yuan, Guankun Wang, Yanheng Li, Haoxuan Che, Nassir Navab 等 10 位作者
Multimodal large language models (MLLMs) have shown strong potential in robotic surgery for question answering, scene understanding, and grounded assistance, but their high computational cost limits real clinical deployment. Knowledge distillation provides a practical way to build compact surgical MLLMs, yet direct distillation is not well suited to surgical data because surgical samples vary greatly in difficulty, visual ambiguity, and required clinical context, making uniform teacher-student transfer unstable. In addition, the role of supervision changes during training: early stages require stronger teacher guidance for multimodal alignment, while later stages rely more on task supervision for effective optimization. To address these challenges, we propose SurgPace, a complexity-aware continuous curriculum framework for progressive distillation of surgical vision-language models. SurgPace estimates sample complexity using predictive confidence and Lorentz geometric consistency, and uses the fused score to guide a continuous easy-to-hard training process. We further introduce hierarchical representation alignment, which aligns the student with the teacher at the feature, logit, and probability levels, while gradually shifting the training focus from teacher imitation to task supervision. This design separates sample-level curriculum from objective-level scheduling, leading to more stable and effective distillation. We evaluate SurgPace on Surg-396K, a benchmark built from four public surgical datasets and covering five dialogue paradigms. SurgPace consistently outperforms strong MLLM distillation baselines, demonstrating its effectiveness for building compact, memory-efficient surgical MLLMs with faster decoding under controlled benchmarks. Code is available at https://github.com/hezhicheng2002/SurgPace.
Real-world forgery is inherently heterogeneous: it manifests not only as digital manipulation but also as physical spoofing, and is carried not only by images but also by videos. Despite substantial progress, a unified anti-forgery foundation model covering such a broad threat spectrum remains absent. In this paper, we present Venus-DefakerOne2, which substantially extends the forensic capability boundary along both the forgery-form and media-type dimensions. Trained on tens of millions of open-source and in-house samples, it incorporates two key designs. Tide-Style-Tuning alternates LoRA and full-parameter fine-tuning to balance computational efficiency, generalization, and hard-sample fitting while mitigating catastrophic forgetting. Entropy-based Test Adaptation determines the optimal prediction modality by analyzing prediction entropy. Venus-DefakerOne2 achieves new state-of-the-art performance across a comprehensive suite of benchmarks, including DeepFake faces (96.7%), AI-generated images (93.3%), tampered documents (87.6%), manipulated natural images (89.6%), physical spoofs (93.1%), and AI-generated videos (96.0%). It significantly outperforms both specialized expert models and its predecessor, DefakerOne, establishing itself as a powerful and versatile foundation model for binary-decision forensic tasks.
Reaction data underpin machine learning for reaction prediction, condition recommendation, and retrosynthetic planning, yet extracting these data from literature figures still requires substantial manual effort. Many figures encode multiple experiments through shared templates, substituent tables, and product grids. Recovering concrete reaction records therefore requires molecular recognition, association of evidence with individual experimental entries, and reconstruction of indirectly specified participants. We present RxnMiner, a multimodal agent system that combines an expert-informed extraction procedure with a chemistry toolbox to coordinate these operations. The agent reads molecular structures, resolves shared and entry-specific evidence, and instantiates participants from templates to assemble source-linked reaction records. We also introduce ChemRxn-Bench, a benchmark of 603 reaction figures with 8,547 manually annotated and reviewed reaction records, evaluated under a common protocol for exact molecular identity and reactant-product pairing. On this benchmark, with Qwen3.8-Flash-Next as the backbone, RxnMiner raises stereochemistry-aware reaction macro-F1 from 21.0% under direct prediction to 71.0%, compared with 25.0% for the strongest existing extraction system. Across five backbones, it also outperforms the same base agent without the extraction procedure and chemistry toolbox by 9.4 to 25.5 points. Applied without human intervention to 10,107 literature figures, RxnMiner produces a silver corpus of 88,202 source-linked reaction records.
Large language model agents increasingly take consequential actions in digital and physical environments, where safety risks may emerge only after multiple interaction steps. This has motivated world-model-driven predictive safety guardrails, which anticipate future consequences before execution. However, existing evaluations largely focus on end-to-end safety outcomes, leaving unclear whether safety gains arise from reliable prediction and faithful use of predicted risks. In this work, we systematically diagnose the prediction-to-action pipeline along three dimensions: how world-model predictions are integrated into decision making, whether the predictions themselves are reliable, and whether their content is faithfully used. Across seven policy models and two safety environments, we find that stronger prediction involvement does not yield monotonic safety gains and can reduce task completion while substantially increasing inference cost. We further find that world-model predictions remain insufficiently reliable, especially over longer horizons, where safety prediction degrades substantially relative to near-term forecasting. Finally, we find that safety gains can persist even under corrupted predictions, while locally verified predictions still leave subsequent safety violations, showing that predictive content is not faithfully incorporated into the decision process. Together, these findings expose a fundamental prediction-to-action gap in current predictive guardrails: producing more or seemingly accurate foresight is insufficient unless that foresight is both reliable and faithfully translated into safer decisions.
Xiangrui Meng, Jingcheng Liu, Ke Wang, Miaopeng Yu, Zhengping Lin
Conclusions in power-system research require a clear evidential basis. Researchers need to understand the data sources, modelling assumptions, and solution procedures to assess the conditions under which a conclusion holds. Large language models (LLMs) can help researchers extract information from documents and translate research requests into code and tool calls, but their outputs still require physical validation. Focusing on human-supervised artificial intelligence (AI) researchers, this review examines power-system LLM applications and related scientific workflows, together with physics-grounded power AI studies, to discuss the conditions for using LLMs in scientific research. In the proposed knowledge-physics-simulation-governance framework, LLMs translate information and coordinate tasks, simulators and validation tools test models, and experts retain authority over critical assumptions, safety boundaries, and final conclusions. Research processes should preserve materials for review so that claims can be traced to their sources, computations can be reproduced, and failed attempts and approvals can be examined. On this basis, a staged development roadmap and requirements for research reporting are proposed. Evaluation should focus on research artifacts and their validation to assess whether LLMs can improve the efficiency of power-system research within clearly defined permissions.
Ao Lu, Yuanhao Zeng, Shaocheng Lan, Sijie Xu, Jiacheng Bao, Kuang Yan, Heng Lin, Kan Ren
Development teams need reproducible tasks from their own repositories and workflows to evaluate coding agents. Conversational developer-agent collaboration ("vibe coding") produces abundant coding sessions and repository checkpoints, but requirements evolve across turns, unrelated conversations co-occur with commits, and engineering efforts can span multiple sessions. We present SessionFarmer, an automated framework that turns these records into self-contained, executable software engineering tasks. It analyzes dialogue and commit history to filter unrelated sessions and group multi-turn, potentially multi-session interactions into work episodes centered on one engineering goal. For each episode, it reconstructs a hermetic execution container, synthesizes a task statement from the full context, and authors repository-grounded engineering-quality rubrics and unit tests. Closed-loop test refinement uses requirement-breaking mutants and a blind solver to reduce false rejections of valid alternatives and false acceptances of incomplete solutions. We construct CropChat, an open benchmark of 242 tasks across 61 public repositories and 14 programming languages, and CropEnterprise from proprietary enterprise logs. In a CropEnterprise audit, the original developers endorse the vast majority of reconstructed episode boundaries, task statements, and quality rubrics. Full-episode context covers substantially more user requirements than single-turn or single-session inputs. Test refinement cuts false-rejection rates and raises balanced accuracy against reference patch labels by 7-9 percentage points across solvers. Across 12 model-harness configurations on CropChat, the strongest setup achieves 39.3% Pass@1, while harness choice shifts Pass@1 by up to 8.4 percentage points for the same model.
Realizing Embodied AI for Science requires robots to translate experimental goals into reliable physical procedures, reducing hazardous and repetitive human work while generating evidence for scientific discovery. Although language-based planning and learned manipulation provide complementary capabilities, their integration requires robots to adapt subsequent operations to actual execution outcomes. For example, an unsuccessful placement changes what must be done next, even when the experimental goal remains unchanged. Existing benchmarks assess planning, manipulation, and laboratory workflows through task completion and reasoning or execution metrics; however, aggregate performance leaves the connection between outcome-dependent choices and physical execution unresolved. To address this evaluation gap, we introduce Labference, a benchmark for evaluating how observed physical outcomes guide subsequent choices and how those choices translate into robotic laboratory actions. Its evaluation protocol is designed to test outcome-dependent behavioral adaptation through controlled evidence variations, while independently measuring operation selection, physical execution, and task completion. Matched Oracle-assisted continuations from shared checkpoints then assess which forms of support improve subsequent choices and task completion. Initial weighing evaluations reveal target-selection errors in the tested VLA policies despite successful object transfers, whereas GPT-driven control achieves correct selection but encounters execution failures and substantial computation costs. Together, these findings highlight the need to connect task-appropriate reasoning with reliable, timely action. By making this connection measurable and diagnosable, Labference supports targeted improvements toward autonomous experimentation for Embodied AI for Science.
Retrieval-augmented generation (RAG) extends large language models with external evidence, yet relevant evidence does not ensure that a generator can use it. Indiscriminate retrieval can degrade task performance while adding retrieval and long-context inference costs. Existing methods neither determine before large-scale execution whether a generator, task distribution, and retriever configuration is worth deploying nor diagnose multiple candidate retrievers under a shared budget. We introduce EviCast, a framework that forecasts retrieval value through interventional evidence-state decomposition. EviCast measures a generator's response to controlled evidence states once and combines this shared profile with the offline evidence-state distribution of each candidate retriever, yielding the end-to-end net utility and its 95% lower confidence bound without executing every RAG configuration. A state-refinement analysis characterizes when its binary and topology-aware instantiations are exact and when shared calibration is statistically more efficient than per-retriever calibration. In frozen evaluations, EviCast correctly decides all 14 HotpotQA retrieval configurations with a forecast error of 2.75 F1 points while reducing diagnostic generation calls by 80%, and it attains the lowest forecast error among seven predictors in the low-budget regime. Its topology-aware instantiation, EviCast-T, captures the complementarity between terminal and bridge evidence, correctly deciding all 16 configurations on MuSiQue and HotpotQA and 23 of 24 after prospective transfer to a third dataset. These results show that retrieval deployment depends on both evidence availability and the generator's ability to convert evidence structure into stable net utility. Code is available at https://github.com/YiboWang2002/EviCast.
Xinhe Zhang, Yuyang Zhang, Pengfei Jin, Arnau Marin-Llobet, Na Li, Quanzheng Li
High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to preserve anatomical consistency across the third dimension. We propose LiFT, a framework for Lifted inter-slice Feature Trajectories that factorizes 3D volume synthesis into per-slice image generation and inter-slice trajectory learning. Rather than using a fully volumetric synthesis backbone, LiFT treats a volume as an ordered trajectory in feature space, capturing how anatomical structures appear, transform, and disappear across depth. We demonstrate the LiFT framework in both unconditional and conditional settings. In unconditional generation, a tri-planar drifting loss matches feature distributions between generated and real volumes across three orthogonal planes; in paired translation, a bidirectional $z$-context mixer trained with paired target supervision supplies through-plane coherence while preserving per-slice fidelity. We evaluate LiFT on BraTS 2023 for unconditional and missing-modality MR synthesis, and on SynthRAD2023 for MR-to-CT translation. LiFT achieves competitive image quality while retaining the efficiency of predominantly 2D synthesis, operating up to $390\times$ faster than a volumetric diffusion baseline and consistently improving through-plane coherence through explicit inter-slice modeling. These results establish lightweight inter-slice trajectory learning as an efficient approach to high-resolution 3D medical synthesis.
The spatial intelligence of large vision-language models (LVLMs) requires the ability to combine local visual observations into a geometrically consistent representation of the physical world. Many static benchmarks assess isolated spatial judgments, such as relative direction or distance, while interactive embodied evaluations combine perception with exploration, planning, control, and simulator-specific execution. To bridge this gap, we introduce RECONSPATIAL, a benchmark centered on multi-view 3D scene reconstruction across indoor, tabletop, and outdoor environments. Given real multi-view images and target-object queries, LVLMs are required to jointly predict oriented 3D bounding boxes in a shared, camera-anchored metric coordinate frame. Reconstructions are evaluated along two complementary axes: Structure for relative layout and Metric for physical scale and camera-anchored placement. Nine atomic spatial QA tasks, grouped into Geometric Perception and Spatial Relations, probe spatial capabilities involved in joint reconstruction. Offline navigation extends evaluation to path planning. Evaluation of 18 frontier LVLMs reveals a consistent gap between relative scene structure and metric reconstruction; even GPT-6-Astra scores 81.4% on Structure but only 58.7% on Metric. Tracing this gap, diagnostic analyses link atomic spatial capabilities to reconstruction quality and show that relational consistency alone does not ensure metric accuracy. Experiments with 3D map injection further separate scene construction from path planning, revealing how these geometric errors limit navigation success. Finally, spatial fine-tuning yields broad transfer across both spatial and general vision-language benchmarks.
We study ordinary kernel ridge regression over full Hölder-Zygmund balls, measuring errors in Sobolev norms and in pointwise and uniform losses for mixed derivatives. For targets of smoothness $s$, every RKHS norm equivalent to $H^{s+d/2}$ gives the optimal $H^r$ risk for $0\le r<s$; integer choices of $r$ include integrated squared derivative losses. Pointwise and uniform guarantees require additional kernel structure. A localized wavelet kernel attains the sharp derivative rates with the same regularization orders as for function estimation, whereas equivalent changes of the RKHS norm can destroy the population bias rates. For the ordinary Gaussian kernel with a shrinking bandwidth, we prove a uniform derivative risk bound with the optimal polynomial rate and an explicit, unoptimized logarithmic factor. The results allow bounded measurable design densities bounded away from zero and conditionally sub-Gaussian noise.
Domain skew challenges federated learning by requiring a shared model to accommodate distinct visual distributions. Domain-specific experts can capture these distributions separately, creating an opportunity to integrate their representations in a unified predictor. We propose Federated Knowledge-Preserving Learning (FKPL), a two-stage framework that combines domain-oriented expert training with prototype-based classifier calibration. First, a one-shot subspace-based clustering procedure groups clients for intra-cluster training. The resulting expert encoders are concatenated and frozen, preserving each learned feature mapping during global integration. Second, clients interpolate their concatenated features with class-matched domain prototypes and upload the resulting virtual features. The server trains a global linear classifier on these features, concentrating classifier optimization at the server after a single feature upload. FKPL achieves average accuracies of 73.01\%, 67.00\%, and 64.51\% on Office-Caltech-10, PACS, and a four-domain subset of DomainNet, respectively. On DomainNet, its cross-domain standard deviation is 7.50 percentage points, the lowest among the evaluated methods. With the same concatenated extractor, prototype-based calibration improves average accuracy over federated classifier training by 9.99 and 14.94 percentage points on Office-Caltech-10 and PACS. These results identify classifier calibration as an effective way to combine preserved domain representations into a global predictor.