论文广场 - AcademicHub

01.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18890

Skill-Guided Continuation Distillation for GUI Agents

作者:

Zhimin Fan ↗Hongwei Yu ↗Yeqing Shen ↗Haolong Yan ↗Guozhen Peng ↗Tianhao Peng ↗Yudong Zhang ↗Xiaowen Zhang ↗Kaijun Tan ↗Zheng Ge ↗Xiangyu Zhang ↗Daxin Jiang ↗…

arXiv:2606.18890v1 Announce Type: new Abstract: Improving GUI agents typically relies on behavior cloning on expert trajectories. However, as the current policy deviates from the expert policy, it inevitably encounters policy-induced off-trajectory states during closed-loop execution, i.e., states that fall outside the expert trajectories. Since expert trajectories provide no demonstrations for these unseen states, such states receive no effective supervision, leaving the policy unable to select the correct action. To close this supervision gap, we propose Skill-Guided Continuation Distillation (SGCD), an iterative self-improvement framework. SGCD first runs the plain policy without skill guidance for a few steps to reach realistic off-trajectory states. From these states, a skill-guided policy then completes the task and produces successful continuations, which are mixed with expert trajectories to supply supervision over policy-induced off-trajectory states. The skills are extracted from both successful and failed rollouts, consisting of Continuation Plans, Critical Targets, Failure Traps, and Success Criteria. On OSWorld-Verified, SGCD improves the success rate of three base models from the low-30\% range to over 50\%, demonstrating its effectiveness and generality.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15396

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

作者:

Wenbo Yu ↗Bohua Wang ↗Hao Fang ↗Kuofeng Gao ↗Jingru Zeng ↗Xiaochen Yang ↗Tianyi Zhang ↗Xiaoxiao Ma ↗Jiawei Kong ↗Hao Wu ↗Bin Chen ↗Shu-Tao Xia ↗…

Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilingual settings, they lack adaptation to Chinese-specific regulatory policies, cultural context and linguistic nuances, failing to support fine-grained risk classification for diverse deployment needs. In this paper, we introduce a 5-macro, 31-micro category fine-grained risk taxonomy for Chinese scenarios, and build CHILLGuard: a dedicated Chinese LLM content safety guardrail. To address the critical scarcity of high-quality annotated Chinese safety data, we propose a scalable multi-stage data construction pipeline: we expand multi-source corpus via retrieval-augmented generation, generate implicit harmful samples through prompt engineering rewriting, and refine high-quality data via multi-model voting-based label calibration. Based on this, we build CHILLGuardTrain, a large-scale training set with 405,007 samples, and CHILLGuardTest, a rigorously curated annotated test set with 51,745 samples. We then train CHILLGuard on CHILLGuardTrain under a generator-classifier collaborative framework via Model-aware Direct Preference Optimization. Extensive experiments under multiple settings demonstrate the state-of-the-art performance of CHILLGuard, e.g., a 15.92% improvement of F1 score over Qwen3Guard-8B-Strict on our benchmark. We will release our resources at https://github.com/cswbyu/CHILLGuard.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16190

Embedded Arena: Iterative Optimization via Hardware Feedback

作者:

arXiv:2606.16190v1 Announce Type: cross Abstract: Embedded devices from wildlife monitoring stations to clinical wearables require local AI inference due to latency, communication, or privacy constraints. Optimizing models for heterogeneous microcontrollers (MCUs) requires simultaneously satisfying hard physical constraints on memory, power, and temperature while preserving accuracy, a multidimensional optimization that is today performed manually by experts. We ask whether an LLM agent can autonomously navigate this complex, multi-turn pipeline guided by real hardware feedback, and introduce a hardware-in-the-loop agent arena in which the agent iteratively refines both model and firmware – compiling, flashing, and measuring on real hardware – to enable closed-loop optimization. Frontier models, including Claude Opus 4.7 and Gemini 3.1 Pro, fail entirely without hardware feedback (0% deployment success), whereas our hardware-in-the-loop formulation achieves the first successful deployment within three iterations and can surpass human expert results within seven. This agentic co-optimization achieves 250x compression for vision models with

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2510.04567

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

作者:

Weishuo Ma ↗Yanbo Wang ↗Xiyuan Wang ↗Lei Zou ↗Muhan Zhang ↗

arXiv:2510.04567v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise to the development of Graph Foundational Models (GFMs). However, current GFMs are challenged by the extreme heterogeneity of graph data, where each graph can possess a unique feature space, label set, and topology. To address this, two main paradigms have emerged. The first leverages Large Language Models (LLMs), but is fundamentally text-dependent, thus struggles to handle the numerical features in vast graphs. The second pre-trains a structure-based model, but the adaptation to new tasks typically requires a costly, per-graph tuning stage, creating a critical efficiency bottleneck. In this work, we move beyond these limitations and introduce Graph In-context Learning Transformer (GILT), a framework built on an LLM-free and tuning-free architecture. GILT introduces a novel token-based framework for in-context learning (ICL) on graphs, reframing classification tasks spanning node, edge and graph levels in a unified framework. This mechanism is the key to handling heterogeneity, as it is designed to operate on generic numerical features. Further, its ability to understand class semantics dynamically from the context enables tuning-free adaptation. Comprehensive experiments show that GILT achieves stronger few-shot performance with significantly less time than LLM-based or tuning-based baselines, validating the effectiveness of our approach. Our code is available at: https://github.com/yiming421/inductnode/.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13030

A Multi-Modal Framework with Cross-Subject Pseudo-Labeling and Semantic Alignment for Micro-Gesture Recognition

作者:

Haoran Zhang ↗Haokun Zhang ↗Pengyu Liu ↗Yujia Zhang ↗Weibao Xue ↗Yanbin Hao ↗

Micro-gestures (MGs) are spontaneous and subtle body movements that frequently convey hidden human emotions. Recognizing MGs in untrimmed videos remains highly challenging due to their extremely low signal-to-noise ratio, severe long-tailed class distribution, and the inherent domain shift encountered in cross-subject evaluation scenarios. In this paper, we propose a comprehensive multi-modal framework for Track 1 of the 4th MiGA-IJCAI Challenge. To capture fine-grained representations, we design a saliency-guided multi-modal extraction pipeline integrating 68-keypoint skeleton joint coordinates, 3D heatmap volumes, and high-resolution RGB visual features. We introduce a gentle square-root smoothed weighting mechanism paired with an Orthogonal Semantic Embedding Loss to protect tail classes without compromising overall recognition capabilities. More importantly, to bridge the cross-subject generalization gap, we propose a Cross-Modal Pseudo-Labeling (CMPL) strategy for unsupervised domain adaptation, which significantly boosts single-modal robustness. A temperature-scaled soft-voting mechanism is finally utilized to alleviate overconfidence during late fusion. Extensive experiments demonstrate that our framework achieves a competitive F1-score of 68.13\%, securing the 4th place.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19771

Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning

作者:

Xuanzhi Feng ↗Zhengyang Li ↗Zeyu Liu ↗Haoxi Li ↗Yuming Jiang ↗Bing Guo ↗Jingcai Guo ↗Jie Zhang ↗Song Guo ↗

arXiv:2606.19771v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instability: uniform token updates precipitate entropy collapse, leading to premature convergence to suboptimal strategies, whereas excessive Shannon Entropy maximization can cause entropy explosion, driving blind exploration toward incoherent reasoning chains. To resolve this dichotomy, we introduce the Independent Combinatorial Tokens (ICT) framework, which shifts the optimization focus from scalar uncertainty to the distributional properties of token logits. By leveraging the Jensen-Shannon (JS) divergence between token logits distributions, ICT identifies tokens with distinctive distributional patterns as critical branching points for guiding effective exploration in LLM reasoning. Our theoretical analysis, grounded in both Shannon and second-order Rényi entropy, proves that selectively updating on these tokens regulates policy concentration: it reduces the overall distribution uncertainty measured by Shannon entropy, while controlling probability concentration captured by second-order Rényi entropy. This dual effect prevents over-concentrated token generation from weakening exploration and effectively stabilizes the training landscape. Empirical results demonstrate that updating only the top 10% of unique tokens on Qwen2.5 (0.5B/1.5B/7B) models yields an average pass@4 improvement of 4.58%, with a maximum gain of 14.9%, over GRPO, 20-Entropy, and STAPO baselines across seven benchmarks spanning math, commonsense, and Olympiad-level problems.

阅读与讨论 → 访问原文 →

07.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2606.15558

Degeneracy Cannot Violate the Quantum Hamming Bound

作者:

Yu-Xuan Zhang ↗Jing-Ling Chen ↗

arXiv:2606.15558v1 Announce Type: new Abstract: The quantum Hamming bound is the standard finite-length sphere-packing bound for exact correction of arbitrary qubit errors. Whether degeneracy can evade this bound has remained unresolved in full generality for nearly three decades: distinct correctable errors may act identically on the code space, so the usual disjoint-sphere argument breaks down. We prove that every exact binary quantum subspace code with $K>1$ obeys the bound, without assuming either nondegeneracy or additivity. Our proof turns the Li–Xing linear-programming polynomial into an exact intersection count for quaternary Hamming balls. Monotonicity in block length and in ball-center separation then reduces the problem to a local node–edge charging inequality at the shortest admissible length. Thus degeneracy can merge correctable error sectors, but cannot enlarge the finite-length binary Hamming bound.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15007

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

作者:

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the context length to 1M tokens, and post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD). Nemotron 3 Ultra is our most capable model yet, employing multiple key technologies - LatentMoE, Multi Token Prediction (MTP), NVFP4 pre-training, multi-environment RLVR, MOPD, and reasoning budget control. Nemotron 3 Ultra achieves up to ~6x higher inference throughput as compared to state-of-the-art publicly available LLMs while attaining on-par accuracy. The state-of-the-art accuracy, high inference throughput, and 1M token context length make Nemotron 3 Ultra ideal for long-running autonomous agentic tasks. We open-source the base, post-trained, and quantized checkpoints, along with the training data and recipe on HuggingFace.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2605.18528

Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise

作者:

Jiayu Zhang ↗Tianyi Lin ↗

arXiv:2605.18528v3 Announce Type: replace-cross Abstract: A growing lesson from neural network optimization is that optimizer design should respect how the model is parametrized. The layerwise input-output structure of neural networks motivates scale-invariant optimizers, such as Muon and Scion, whose updates also support hyperparameter transfer. At the same time, stochastic gradient noise in deep learning is often far from sub-Gaussian and may exhibit heavy tails. These observations have shaped recent algorithmic principles for training neural networks, yet their joint theoretical consequences are underexplored. In particular, it remains unclear what dimension dependence is unavoidable for gradient-based methods given the problem class is defined by input-output norm and under heavy-tailed noise, and whether higher-order smoothness can accelerate training. We study these questions through nonconvex smooth stochastic optimization over $\mathbb R^{m\times n}$ equipped with general norms and under $p^\mathrm{th}$-moment heavy-tailed noise, where the goal is to achieve an $\epsilon$-stationary point in the dual norm. Our first contribution is a dimension-dependent lower bound: when $\frac{\max\{m,n\}}{(\min\{m,n\})^2}$ is large enough, any gradient-based method requires $\Omega(\min\{m, n\}\epsilon^{-\frac{3p-2}{p-1}})$ oracles for the problem class defined by the spectral norm, which is a common input-output norm. We prove that a scale-invariant Scion method with the spectral norm can achieve the matching upper bound of $O(\min\{m, n\}\epsilon^{-\frac{3p-2}{p-1}})$. To exploit higher-order smoothness, we propose a transported Scion method and improve the bound to $O(\min\{m, n\}\epsilon^{-\frac{5p-3}{2p-2}})$ when the Hessian is Lipschitz. Finally, we incorporate heuristics into our transported method and evaluate it across multiple architectures and model sizes, demonstrating its flexibility and compatibility with neural network training.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17950

Plug-and-Adapt: Multimodal Coreference Resolution at First Sight with a Pretrained Alignment Model

作者:

Jinghan Wu ↗Jing Li ↗Ivor W. Tsang ↗Xuetao Zhang ↗

Visual information helps resolve ambiguity in coreference resolution, leading to notable performance gains. However, existing Multi-modal Coreference Resolution (MCR) methods require training with (partially) annotated data from the target dataset before they can be applied, preventing their direct usability and raising concerns about generalization. While Vision-Language Large Models (VLLMs) with billions of parameters offer promising zero-shot capabilities, they remain largely inaccessible. Their massive size limits deployability, and many are only accessible through paid APIs. In this paper, we propose a plug-and-adapt method that strategically adapts a carefully pre-trained alignment model for immediate use in MCR tasks, designed to eliminate the need for training on scarce benchmark datasets or relying on resource-intensive VLLMs. Specifically, we first pre-train a fine-grained alignment model between textual and visual contextual information using vision-language alignment datasets. We then repurpose the alignment model to MCR through similarity aggregation by fusing visual and categorical cues with evidence theory, thereby enhancing effectiveness. Experiments on the Coreference Image Narratives (CIN) benchmark dataset demonstrate the effectiveness of our method, achieving a 5.31\% and 2.12\% improvement in CoNLL F1 over SOTA dedicated methods and popular VLLMs, respectively. We further evaluate our method on a masked CIN dataset for robustness testing and on a specially constructed VCR-MCR dataset for generalization assessment, with results confirming both capabilities.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19348

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

作者:

DeepSeek-AI ↗Anyi Xu ↗Bangcai Lin ↗Bing Xue ↗Bingxuan Wang ↗Bingzheng Xu ↗Bochao Wu ↗Bowei Zhang ↗Chaofan Lin ↗Chen Dong ↗Chenchen Ling ↗Chengda Lu ↗…

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models – DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) – both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19659

SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation

作者:

Yuhang Zhou ↗Lizhu Zhang ↗Yifan Wu ↗Mingyi Wang ↗Bo Peng ↗Jiayi Liu ↗Xiangjun Fan ↗Zhuokai Zhao ↗

On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in agent training. However, most OPD studies focus on single-turn settings, while realistic LLM agents interact with environments over multiple turns. In this regime, early errors can alter future observations and compound across the trajectory, and standard dense token-level OPD becomes brittle, as it may over-penalize semantically valid alternatives, reinforce local degeneracies such as repeated actions, and propagate unreliable teacher supervision on off-distribution histories. We propose SAGE-OPD, a verifier-free selective intervention framework specifically designed for multi-turn OPD. Instead of applying teacher supervision uniformly across all turns, SAGE-OPD first observes environment feedback and uses teacher judgment to decide whether each student response should be skipped or intervened on. To further address compounding errors, SAGE-OPD weights token-level distillation by teacher confidence, reducing the influence of uncertain teacher distributions on corrupted or ambiguous histories. Finally, SAGE-OPD applies loss normalization to preserve the overall loss scale of standard OPD while retaining selective turn-level weighting. Experiments on agent tasks show that SAGE-OPD consistently improves over baselines, achieving up to a 13.3% relative improvement in ALFWorld unseen success rate over standard OPD. Ablation studies further demonstrate that turn-level intervention, teacher confidence weighting, and loss normalization provide complementary benefits. Our results suggest that effective multi-turn OPD should remain on-policy, but teacher supervision should be selectively allocated to turns where intervention is necessary and reliable.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.18089

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

作者:

Lingjing Kong ↗Xin Liu ↗Guangyi Chen ↗Martin Q. Ma ↗Xiangchen Song ↗Yuekai Sun ↗Mikhail Yurochkin ↗Taylor W. Killian ↗Ruslan Salakhutdinov ↗Kun Zhang ↗Eric P. Xing ↗Zhengzhong Liu ↗…

arXiv:2606.18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners. We argue that this combined success is driven by compositional generalization, which we formalize through a hierarchical latent selection model. In this framework, reasoning traces are generated by a cascade of discrete latent selection variables corresponding to reusable atomic modules, including both skills (local operations) and routing mechanisms (how intermediate information is selected, reused, and composed). Within this model, we theoretically show that SFT and RL play asymmetric, complementary roles: SFT supplies the raw module materials in compositional traces, and RL decomposes those traces to identify the latent atomic modules and enable compositional generalization. We design controlled experiments to validate this theory. Our results demonstrate that RL can extract atomic modules from compound traces supplied by SFT and recombine them to solve new configurations. Moreover, we find that training on compound traces yields stronger generalization than training on isolated atomic modules. Finally, we investigate the relationship between SFT and RL data and identify an effective protocol in which SFT ensures coverage of all atomic modules through compositional traces, while RL focuses on novel compositions outside the SFT support to drive exploration.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15872

SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks

作者:

Jingru Guo ↗Xiangyuan Xue ↗Lian Zhang ↗Wanghan Xu ↗Siki Chen ↗Philip Torr ↗Wanli Ouyang ↗Lei Bai ↗Zhenfei Yin ↗

Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even the strongest commercial systems fall short of expert-level performance. A closer look at model behavior reveals substantial complementarity that single-model evaluation hides: different frontier models excel on different question types, and no single model captures the full picture. We present SciOrch, a framework that trains a lightweight 8B model to orchestrate frontier LLMs for scientific reasoning. The orchestrator decomposes each question, delegates sub-problems to selected commercial models through API calls, and synthesizes a final answer. Training such an orchestrator is fundamentally harder than conventional agentic RL: each action triggers an API call that is expensive in both dollar cost and latency, making standard online rollouts infeasible. We address this with MCTS-based approach, producing diverse orchestration trajectories, extracting per-node single-turn samples, and optimizing the orchestrator with GRPO-style training. On a 240-question test set spanning SGI-Reasoning and Scientists' First Exam, SciOrch reaches 56.66% average accuracy, outperforming the strongest single commercial model by 3.74% and the strongest multi-agent baseline by 3.33%. It also attains the best accuracy on both SGI and SFE with less than half the API cost of typical multi-agent methods.

阅读与讨论 → 访问原文 →

15.

bioRxiv (Bioinfo) 2026-06-12 DOI: HASH:33fd357505c634fe073b6765b575a7fa

PHI-Reason: evidence-grounded species-level phage-host prediction from structured biological text profiles

作者:

Zhang ↗Y.-z ↗Xu ↗Imoto ↗

Phage–host interaction (PHI) prediction is a fundamental problem in microbiology with applications in microbial ecology and microbiome engineering. Existing computational approaches typically convert phage and host information into numerical representations derived from sequence similarity, protein content, genome composition or reference databases, then score candidate hosts or train host-prediction models. Although effective, such representations often make it difficult to inspect which biological evidence supports a prediction. Here, we present PHI-Reason, a species-level PHI prediction framework that reformulates host prediction as constrained biological text reasoning. Instead of embedding phages and hosts directly as numerical vectors, PHI-Reason converts heterogeneous PHI-related evidence from phage genomes, host genomes, functional annotations, homology searches and biological metadata into modular natural-language profiles. A frozen large language model then performs species-level candidate-host ranking or pairwise PHI assessment by integrating the supplied evidence at inference time. Across species-level benchmarks, PHI-Reason achieved competitive host-prediction performance and recovered complementary correct assignments relative to established sequence- and reference-based methods. Its explicit profile design enabled systematic evidence perturbation and rationale-grounding analyses, showing that predictions depend on coherent multi-source biological evidence and that hallucination risk from unsupported or incomplete profiles can be made operationally measurable. These results position PHI-Reason as a constrained evidence-integration framework for species-level PHI prediction. Rather than replacing sequence-based predictors, it provides an interpretable layer that shows how far explicit biological evidence can support host inference, and where that evidence falls short.

阅读与讨论 → 访问原文 →

16.

medRxiv (Medicine) 2026-06-16 DOI: HASH:57f5c75d29d8f40beb20ce338ce748df

Comparative Effectiveness and Safety of Prophylactic Vasopressors for Preventing Post-induction Hypotension in the Elderly: A Systematic Review and Network Meta-analysis

作者:

Zhang ↗Wang ↗Duan ↗C. L ↗Di ↗Y. R ↗

Background: Post-induction hypotension is a predictable haemodynamic hazard in older adults undergoing general anaesthesia. Prevention remains divided among volume optimisation, anaesthetic dose reduction, rescue treatment after hypotension occurs and proactive vasoactive support. Methods: We searched PubMed, Embase, Web of Science, CENTRAL, CNKI, Wanfang and VIP from inception to 30 March 2026. Eligible studies were randomised trials of prophylactic vasoactive drugs given before, during or immediately after induction in older adults. The primary outcome was post-induction hypotension. Secondary outcomes were post-induction mean arterial pressure (MAP), systolic arterial pressure (SBP), heart rate (HR) and reported haemodynamic adverse events. Random-effects network meta-analysis was used, and confidence in network estimates was assessed using CINeMA principles. Results: Thirty-one trials including 2,821 participants were included in the revised network. Compared with placebo/control, all active agents favoured lower post-induction hypotension. The most favourable point estimates were observed for phenylephrine (odds ratio [OR] 0.17, 95% confidence interval [CI] 0.01 to 2.16) and metaraminol (OR 0.19, 95% CI 0.02 to 1.53), although both were imprecise. More precise reductions were observed for methoxamine (OR 0.23, 95% CI 0.13 to 0.43), norepinephrine (OR 0.25, 95% CI 0.13 to 0.47) and ephedrine (OR 0.34, 95% CI 0.19 to 0.63). Phenylephrine ranked highest for MAP support, norepinephrine ranked highest for SBP support, and ephedrine ranked highest for HR preservation. Global inconsistency was detected for SBP but not for hypotension incidence, MAP or HR, supporting cautious profile-based interpretation. Conclusions: Prophylactic vasopressor choice during induction should be guided by haemodynamic phenotype rather than ranking alone. In the revised network, active prophylaxis consistently favoured lower hypotension, but sparse nodes produced uncertainty. Norepinephrine retained a comparatively balanced profile when vasodilatory post-induction hypotension is anticipated, phenylephrine and related alpha-agonists provided stronger pressure support when HR and cardiac-output reserve are preserved, and ephedrine was most relevant when chronotropic support is desired. Keywords: general anaesthesia; induction; hypotension; norepinephrine; phenylephrine; ephedrine; network meta-analysis; older adults.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18861

URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification

作者:

Xinze Zhang ↗

Reconstructing simulation-ready digital twins of articulated objects from sensor observations remains constrained by two persistent gaps: (i) part-level geometric reconstruction is decoupled from kinematic-parameter estimation, and (ii) the recovered models often violate basic dynamic invariants such as energy conservation, leading to drift when the URDF is replayed in physics simulators. We present KinemaForge, a constraint-driven pipeline that jointly infers part-level shape, joint topology, and joint parameters from short RGB-D sequences and validates the result against an energy-consistent verifier built on differentiable rigid-body dynamics. The pipeline introduces three components: a kinematic constraint graph that encodes joint-part incidences as soft edges; a differentiable screw-axis solver that backpropagates from rendered observations through Featherstone's articulated-body algorithm to joint parameters; and an energy residual loss that penalises non-physical free responses of the reconstructed model. Across five PartNet-Mobility categories and an internal RGB-D benchmark, KinemaForge reduces the average joint-axis error from 4.52 degrees to 2.83 degrees (-37.4%) over the strongest geometric baseline (PARIS) and from 5.30 degrees to 2.83 degrees (-46.6%) over the interaction-based Ditto baseline, lowers long-horizon simulation drift by 64% (vs. PARIS) over 50 s rollouts, and yields URDFs whose closed-loop manipulation success rate improves by 14.6 percentage points over Ditto in our preliminary evaluation. Code and reconstruction data will be released upon acceptance.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16160

A comparative and critical study of EEGNet for fNIRS-driven cognitive load classification

作者:

Mehshan Ahmed Khan ↗Houshyar Asadi ↗Li Zhang ↗Mohammad reza Chalak Qazani ↗Ghazal Bargshady ↗Stefanos gkikas ↗Christian arzate ↗Sam Oladazimi ↗Zoran Najdovsk ↗Lei Wei ↗Chee Peng Lim ↗

arXiv:2606.16160v1 Announce Type: cross Abstract: Accurately classifying cognitive load from functional near-infrared spectroscopy (fNIRS) signals remains a significant challenge due to temporal variability, inter-subject differences, and sensitivity to preprocessing choices. This study provides a comprehensive evaluation of EEGNet for fNIRS-based cognitive load classification by systematically examining the effects of temporal segmentation strategies (overlapping vs. non-overlapping), window lengths (10s, 20s, 30s), feature extraction methods (Analysis of Variance (ANOVA), Principal Component Analysis (PCA), Fast Independent Component Analysis (FastICA)), learning rate configurations (fixed and adaptive), and evaluation protocols (random split vs. subject-independent (SI)). Results from random-split experiments show that overlapping segmentation, combined with smaller fixed learning rates (0.01-0.001), yields the highest accuracies, due to temporal redundancy and dense sampling of hemodynamic transitions. However, SI evaluation reveals a substantial drop in accuracy, demonstrating limited generalization to unseen participants. Under SI evaluation, non-overlapping segmentation outperformed overlapping windows, with the best accuracy of 56.11% achieved using PCA features with a 20-second window and a 0.1 learning rate. These findings indicate that eliminating temporal redundancy helps the model learn more robust and generalizable representations of cognitive load across individuals. Although adaptive learning rate strategy improved training stability, it did not surpass the performance of optimally selected fixed learning rates. The study highlights the critical role of segmentation strategy and learning rate selection in improving model generalization and identifies methodological considerations essential for developing reliable, real-time, and SI cognitive load classification systems using fNIRS.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.17022

Learning the Geometry of Data: A Mathematical Review of Shape Space Analysis

作者:

Gary P. T. Choi ↗Khanh Dao Duc ↗Shira Faigenbaum-Golovin ↗Karen Habermann ↗Emmanuel Hartman ↗Christoph von Tycowicz ↗Chi Zhang ↗Wenjun Zhao ↗Felix Zhou ↗

arXiv:2606.17022v1 Announce Type: cross Abstract: A central objective of machine learning is to identify structure and patterns in data. Advances in data acquisition have increasingly produced datasets whose observations possess rich geometric form, giving rise to shape spaces that encode variability in object geometry. Such datasets arise across a wide range of disciplines, including biology, medicine, anthropology, and computer vision, where subtle geometric differences often carry important scientific information. Traditional machine learning methods, however, are frequently ill-equipped to account for the nonlinear geometric structure underlying these data. This survey synthesizes a rapidly growing body of work on shape space analysis, which provides a mathematical and computational framework for the study of geometric data. Drawing on ideas from differential geometry, statistics, and machine learning, we organize the literature around a common analytical pipeline: shape representation and parameterization, the rigorous construction of robust geodesic metrics, statistical analysis on shape spaces, and geometry-aware learning methods. We discuss how these tools enable the characterization of shape variability, the comparison of geometric objects, and the analysis of structural trajectories across populations and time. To illustrate the breadth of the field, we highlight applications spanning multiple scales of biological organization, including studies of subcellular morphology and primate tooth evolution. Across these and many other domains, researchers face common challenges arising from complex, nonlinear, and often unaligned geometric variation. The review concludes by identifying key theoretical and computational challenges, as well as emerging opportunities driven by increasingly large and diverse geometric datasets.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18831

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

作者:

Xiaoyue Xu ↗Sikui Zhang ↗Xiaorong Wang ↗Xu Han ↗Chaojun Xiao ↗

Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over lengthy trajectories. Reinforcement learning (RL) has recently emerged as a dominant paradigm for improving this ability, yet existing work largely focuses on reward engineering while diverse training data remains scarce. We revisit this problem from a data-centric perspective and show that a simple yet effective data recipe alone, paired with a minimal outcome-based GRPO setup, suffices to substantially improve long-context reasoning. Our recipe targets three complementary task families – retrieval, multi-evidence synthesis, and reasoning – for which we construct and curate eight datasets totaling ~14K examples. Experiments on three models (Qwen3-4B/8B/30B-A3B) yield average gains of +7.2/+3.2/+6.4 points across seven long-context benchmarks, surpassing prior RL training sets. We further demonstrate that these gains transfer to agentic tasks, where continuing RL training on an agent-tuned model with our data recipe improves GAIA by +4.8 and BrowseComp by +7.0 points. We will release our datasets to facilitate future research.

阅读与讨论 → 访问原文 →

21.

Nature (Science) 2026-06-17 DOI: HASH:1ef221dc0065d687270ab7848ecb3503

Confined migration induces non-lethal DNA damage in developing neurons

作者:

Zhejing Zhang ↗

Migratory cells tend to have soft nuclei that deform and penetrate narrow spaces1,2. Extensive nuclear deformation during migration can cause nuclear-envelope rupture and DNA damage in cancer cells, which may contribute to malignant transformation during tumour progression3–6. However, the importance of DNA damage in physiological migration is less well understood. Here we demonstrate that the migration of neurons in developing cerebral and cerebellar cortices is accompanied by massive DNA double-stranded breaks (DSBs) due to mechanostress during passage through narrow interstitial spaces. In contrast to many other migratory cells, these DSBs occur without detectable nuclear envelope rupture. Confined migration increases topoisomerase-IIβ covalently bound DSBs, and these lesions are repaired through non-homologous end-joining during brain development without causing cell death. Genome sequencing revealed that DSBs tend to occur at transcriptionally inactive regions. The deletion of ligase IV at the onset of neuronal migration leads to persistent DSB accumulation in cerebellar neurons with moderate transcriptional changes in genes related to synaptic function, neuronal development and stress and immune responses. The mutant mouse develops mild motor deficits in later life, suggesting that the DNA damage generated during normal brain development poses a potential disease risk if left unrepaired. The migration of neurons in developing cerebral and cerebellar cortices is accompanied by massive DNA double-strand breaks due to mechanostress during passage through narrow interstitial spaces.

阅读与讨论 → 访问原文 →

22.

arXiv (quant-ph) 2026-06-16 DOI: arXiv:2506.06010

Magnetic control of an exciton-polariton condensate in a van der Waals magnet

作者:

arXiv:2506.06010v3 Announce Type: replace-cross Abstract: Quasiparticle condensates are among the most spectacular solid-state manifestations of quantum physics. Coupling macroscopic real-space wavefunctions to additional degrees of freedom, such as the electron spin, would add valuable control knobs for quantum applications. While creating spin-carrying superconducting condensates has attracted enormous attention, man-made condensates of light-matter hybrids known as exciton-polaritons have lacked an analogous spin-based perspective. Here we open a new door by demonstrating magnetically tunable exciton-polariton condensation in the van der Waals magnet CrSBr. Under photoexcitation, CrSBr microwires embedded in an optical cavity show the hallmarks of polariton condensation: a dramatic increase of the emission intensity from an excited laterally confined polariton state by multiple orders of magnitude, spectral narrowing of the emission line, and a continuous shift of the peak energy. Interferometry evidences an increase in spatial and temporal coherence. Owing to the strong coupling between the spin order and excitonic correlation, the energy of the condensate can be tuned by up to 10.5 meV by an external magnetic field of only 2 Tesla. Our results establish CrSBr microcavities as a powerful platform for exploring magnetic control of polariton condensates and mark a significant step toward spin-controlled coherent quantum light sources.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2605.03065

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

作者:

arXiv:2605.03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient algorithm for finetuning GCPs that maintains off-policy critic networks to maximize data reuse and propagate policy gradients through the full generative process of the policy via a modified PPO objective, using critics as the terminal reward. OGPO achieves state-of-the-art performance on manipulation tasks spanning multi-task settings, high-precision insertion, and dexterous control. To our knowledge, it is also the only method that can fine-tune poorly-initialized behavior cloning policies to near full task-success with no expert data in the online replay buffer, and does so with few task-specific hyperparameter tuning. Through extensive empirical investigations, we demonstrate that OGPO drastically outperforms methods alternatives on policy steering and learning residual corrections, and identify the key mechanisms behind its performance. We further introduce practical stabilization tricks, including success-buffer regularization, two-sided conservative advantages, and Q-variance reduction, to mitigate critic over-exploitation across state- and pixel-based settings. Beyond proposing OGPO, we conduct a systematic empirical study of GCP finetuning, identifying the stabilizing mechanisms and failure modes that govern successful off-policy full-policy improvement.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16256

KeepLoRA++: Continual Learning with Layer-Scaled Residual Gradient Adaptation

作者:

Mao-Lin Luo ↗Yi-Lin Zhang ↗Zi-Hao Zhou ↗Yankun Hong ↗Xialiang Tong ↗Mingxuan Yuan ↗Tong Wei ↗Min-Ling Zhang ↗

Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plasticity to acquire new knowledge. This paper presents KeepLoRA++, balancing these objectives through a unified dual-dimensional knowledge retention mechanism. We analyze knowledge distribution of Transformer architecture from both inter-layer and intra-layer perspectives. The inter-layer perspective examines how retention is distributed across layers, while the intra-layer perspective focuses on the parameter space within each layer. Our analysis reveals a structural property: general transferable knowledge is mainly encoded in the shallow layers and the principal subspace of the parameters, while task-specific adaptations are localized in the deep layers and the residual subspace. Motivated by this insight, KeepLoRA++ introduces a layer-scaled residual gradient adaptation method. New tasks are learned by restricting LoRA parameter updates to the residual subspace, combined with a shallow-to-deep layer scaling, to prevent interference with previously acquired capabilities. Specifically, the gradient of a new task is projected onto a subspace orthogonal to both the principal subspace of the pre-trained model and the dominant directions of previous task features, while simultaneously assigning smaller update magnitudes to shallow layers and larger ones to deeper layers. Our theoretical analysis and empirical evaluations confirm that KeepLoRA++ successfully balances these three competing objectives, consistently outperforming representative baselines across image classification, visual question answering, and video understanding tasks.

阅读与讨论 → 访问原文 →

25.

medRxiv (Medicine) 2026-06-12 DOI: HASH:5bcfd291357fe5a016c70ad7117d2d23

Disentangling Confounders from Pathology in Long-COVID Trajectory Prediction for Women: An Interpretable Large-Language-Model Approach

作者:

Wang ↗Galis ↗Zhang ↗Luo ↗Sra ↗Niu ↗Shen ↗Xie ↗Weiss ↗J. C ↗

Objective. Post-acute sequelae of SARS-CoV-2 infection (PASC, "Long COVID") dispropor- tionately affects women, in whom hallmark symptoms–insomnia, fatigue, palpitations, cogni- tive difficulty–overlap with comorbidities and hormonal transitions such as menopause. This diagnostic overlap is a confounding problem: models that forecast future symptom severity risk attributing baseline physiological noise to viral pathology. We ask whether an interpretable, causally disentangled language model can separate true pathological signal from such con- founders while remaining competitive with strong predictors of future PASC severity

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络