论文广场 - AcademicHub

01.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11672

Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical Assessment

作者:

Derek Yohn ↗Luke Flancher ↗Mirajul Islam ↗Khaled Slhoub ↗

arXiv:2606.11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- (GenAI-) based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using precision, recall, false positive count, and a calculated composite score based upon the interplay of the captured metrics, against the baseline performance of an existing, vetted Static Application Security Testing (SAST) tool, Bandit. Our findings refute the notion that a modern open-source GenAI LLM-based agent is currently suitable for the specialized task of SAST scanning under realistic conditions.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.05405

Agents' Last Exam

作者:

Yiyou Sun ↗Xinyang Han ↗Weichen Zhang ↗Yuanbo Pang ↗Tianyu Wang ↗Yuhan Cao ↗Yixiao Huang ↗Chris Duroiu ↗Haoyun Zhang ↗Jeffrey Lin ↗Weishu Zhang ↗Tyler Zeng ↗…

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19416

MortarBench: Evaluating Mortgage Loan Origination Agents

作者:

Matthew Toles ↗Yunan Lu ↗Manav Munjal ↗Bojun Liu ↗Yuanhao Deng ↗Stephanie Selig ↗Derek Rindner ↗Cheng Li ↗Zhou Yu ↗

arXiv:2606.19416v1 Announce Type: new Abstract: Loan origination is the process by which a lender creates a new loan, from application and underwriting through approval and funding. This process serves a critical role in evaluating the eligibility and level of risk posed by an applicant. Recently, firms have begun using mortgage loan agents to augment human loan officers, despite a lack of any public benchmark. To fill this gap, we present MortarBench, a loan origination agent benchmark. MortarBench uses a financial data synthesis and mutation pipeline to generate examples with broad edge case coverage that match real-world distributions and questions. We find that state-of-the-art large language models (LLMs) perform poorly, with closed-source models achieving at most 77.1\% exact match accuracy. We also discover systematic biases in LLM perception of foreignness related to non-English names. Noting these weaknesses, we introduce CRIT, a confidence calibration framework. Our method increases accuracy to 80.5\% while improving risk management steering and reducing bias.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.14999

Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders

作者:

Monika Choudhary ↗Xiaoya Chong ↗Runbo Jiang ↗Wiebke Koepp ↗Petrus H. Zwart ↗Damon English ↗Gregory M. Su ↗Eric Schaible ↗Chenhui Zhu ↗Mostafa Nassr ↗Noah P. Wamble ↗Kelvin Kam-Yun Li ↗…

arXiv:2606.14999v1 Announce Type: new Abstract: Scientific user facilities generate X-ray scattering data faster than traditional workflows can process them. We address this challenge across two settings, offline dataset exploration and live on-the-fly analysis. We train a domain-specific attention-based Convolutional Variational Autoencoder (C-VAE) on 1.5 million X-ray scattering images to learn low-dimensional representations capturing structural variation across diverse experimental conditions. The learned latent space reveals well-organized clusters and smooth trajectories reflecting experimental progression. It further supports controlled synthetic scattering image generation across diverse structural states. When deployed without retraining, the model organizes time-resolved film formation experiments at two synchrotron facilities into interpretable latent structures. Benchmarking against DINOv3 (ViT-7B), a general-purpose vision foundation model, demonstrates that domain-specific training yields more interpretable latent organization for scattering data. Both workflows are integrated within Latent Space Explorer, a component of the MLExchange platform, supporting interactive structural exploration across archived datasets and live experiments.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2604.18866

HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images

作者:

Pourya Shamsolmoali ↗Masoumeh Zareapoor ↗Michael Felsberg ↗Nick Pears ↗Huiyu Zhou ↗Yue Lu ↗

Despite advances in object detection, aerial imagery remains a challenging domain, as models often fail to generalize across variations in spatial resolution, scene composition, and semantic label coverage. Differences in geographic context, sensor characteristics, and object distributions across datasets limit the capacity of conventional models to learn consistent and transferable representations. Shared methods trained on such data tend to impose a unified representation across fundamentally different domains, resulting in poor performance on region-specific content and less flexibility when dealing with novel object categories. To address this, we propose a novel modular learning framework that enables structured specialization in aerial detection. Our method introduces a hierarchical routing mechanism with two levels of modularity: a domain routing layer that uses latent geographic embeddings to assign inputs to domain-specialized expert modules, and a scene routing mechanism that allocates image subregions to scene-specific expert modules. This allows our method to specialize across datasets and within complex scenes. Additionally, the framework contains a conditional expert module that uses external semantic information (e.g., category names or textual descriptions) to enable detection of novel object categories during inference, without the need for retraining or fine-tuning. By moving beyond monolithic representations, our method provides an adaptive framework for remote sensing object detection. Comprehensive evaluations on four datasets highlight improvements in multi-dataset generalization, region-level specialization, and open-category detection.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20388

DataMagic: Transforming Tabular Data into Data Insight Video

作者:

Yupeng Xie ↗Chen Ma ↗Zhenyang Wang ↗Liangwei Wang ↗Jiayi Zhu ↗Chuxuan Zeng ↗Zhouan Shen ↗Boyan Li ↗Yuyu Luo ↗

arXiv:2606.20388v1 Announce Type: cross Abstract: Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate data insights as temporal narratives, making them an effective medium for improving data consumption efficiency in the data management lifecycle. However, producing high-quality data videos requires expertise spanning data analysis, narrative design, and video production. Existing approaches fall short: static visualization tools (e.g., BI dashboards) lack narrative logic and animation; authoring tools require users to pre-prepare visualizations rather than working from raw data; pixel-level video generation models cannot guarantee data fidelity or provenance. We demonstrate DataMagic, an end-to-end interactive system that transforms raw tabular data and natural language queries into narrative data-insight videos. To ensure data fidelity, DataMagic introduces the declarative specification DVSpec, which binds visual and animation elements to underlying data fields through data-driven semantic references. To address the combinatorial explosion of the design space, DataMagic adopts a Generate-then-Orchestrate multi-agent architecture that generates candidate scenes in parallel and then optimizes narrative coherence through global orchestration. Leveraging DVSpec's decoupling of logic and rendering, the system further supports three interaction modes and structured provenance-based data Q&A, transforming one-way videos into explorable interactive data interfaces. Evaluation on 109 real-world samples validates the effectiveness of the DataMagic. Homepage: https://datamagic-home.github.io/

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13376

MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold

作者:

Yang Zhou ↗Ziheng Wang ↗Yuqin Lu ↗Haofeng Liu ↗Jun Liang ↗Shengfeng He ↗Jing Li ↗

We present MoVerse, a real-time video world model that creates an interactively navigable scene from a single narrow-field-of-view image. This setting is challenging because the input observes only a small fraction of the environment, while interactive roaming requires a complete surrounding world, persistent geometry, controllable camera motion, and temporally coherent high-fidelity observations. MoVerse addresses this problem by separating world construction from observation rendering. It first expands the input into a gravity-aligned 360$^\circ$ panorama with topology-aware diffusion, closing the missing field of view before 3D reasoning. It then lifts the panorama into a persistent 3D Gaussian scaffold using panoramic geometry-aware residual prediction, yielding a dense and directly renderable spatial memory. Finally, a Gaussian-conditioned video renderer translates scaffold renderings along user-specified camera trajectories into photorealistic video. To make this renderer practical for interaction, we train a bidirectional diffusion teacher for high-quality conditional rendering and distill it into a causal autoregressive student for bounded-latency streaming. This design combines the controllability and long-range consistency of explicit 3D representations with the perceptual quality of generative video models. MoVerse supports real-time scene roaming at 8~FPS on a single NVIDIA RTX~4090 GPU, demonstrating a practical path toward single-image world creation with interactive video output.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13432

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

作者:

Jiwen Liu ↗Shujuan Li ↗Zhixue Fang ↗Xiaohan Li ↗Yan Zhou ↗Zijie Meng ↗Zhimin Zhang ↗Yawen Luo ↗Guoxin Zhang ↗Yu-Shen Liu ↗Pengfei Wan ↗

Cloning camera motion from reference videos is an important task in video generation, as videos provide intuitive and precise control. Existing methods either directly use parametric representations that fail to handle multi-shot generation or synthesize cross-paired data, which suffer from data scarcity, resulting in poor performance in complicated camera motion cloning. To address these issues, we introduce a general camera motion representation that encodes cameras as grid motion videos. This camera grid represents the camera parameters visually and supports the integration of diverse trajectories for multi-shot video generation. Building upon this, we propose OmniDirector, a unified framework trained on a million-scale camera grid-video pairs that coordinates characters, actions, and cameras to provide director-level control for multimodal diffusion transformers. Furthermore, we design a novel hierarchical prompt expansion agent that harmoniously integrates different control signals by systematically describing camera motion and visual content through understanding signal relationships. Extensive experiments demonstrate the superior performance and outstanding controllability of our framework. Project page: https://ymlinfeng.github.io/OmniDirector.github.io/

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.13993

The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models

作者:

Zachary Nicholas Houghton ↗Yu Zhou ↗Dan Pluth ↗Vijay K. Gurbani ↗

A crucial aspect of linguistic capability is the ability to trade off between stored representations and abstract knowledge: one must retrieve learned representations, but also generate novel ones by applying productive rules. While recent work has examined abstract knowledge in language models, holistic storage of multi-word units has received far less attention. We probe internal representations in text-based LLMs and an ASR model, testing whether V+up phrasal verbs develop distinct representations as a function of frequency and predictability. All models show evidence of holistic storage driven by frequency and predictability, further supporting usage-based theories of language.

阅读与讨论 → 访问原文 →

10.

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 →

11.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2604.24806

Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale

作者:

Liang Guo ↗Ge Song ↗Litao Deng ↗Jianhui Sun ↗Chufeng Hu ↗Lu Zhang ↗Zhen Ma ↗Shouwei Chen ↗Weiran Liu ↗Sarang Masti Sreeshylan ↗Xiaoxuan Meng ↗Yanzun Huang ↗…

arXiv:2604.24806v2 Announce Type: replace-cross Abstract: Modern Deep Learning Recommendation Models (DLRMs) follow scaling laws with sequence length, driving the frontier toward ultra-long User Interaction History (UIH). However, the industry-standard "Fat Row" paradigm, which pre-materializes these sequences into every training example, creates a storage and I/O wall where data infrastructure usage exceeds GPU training capacity due to data redundancy that is amplified in multi-tenant environments where models with vastly different sequence length requirements share a union dataset. We present a versioned late materialization paradigm that eliminates this redundancy by storing UIH once in a normalized, immutable tier and reconstructing sequences just-in-time during training via lightweight versioned pointers. The system ensures Online-to-Offline (O2O) consistency through a bifurcated protocol that prevents future leakage across both streaming and batch training, while a read-optimized immutable storage layer provides multi-dimensional projection pushdown for heterogeneous model tenants. Disaggregated data preprocessing with pipelined I/O prefetching and data-affinity optimizations masks the latency of training-time sequence reconstruction, keeping training throughput compute-bound by GPUs. Deployed on production DLRMs, the system reduces training data infrastructure resource usage while enabling aggressive sequence length scaling that delivers significant model quality gains, serving as the foundational data infrastructure for modern recommendation model architectures, including HSTU and ULTRA-HSTU.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18509

Concept Modulation Models: A Unified Framework for Identifiability and Extrapolation

作者:

Soheun Yi ↗Yizhou Lu ↗Chandler Squires ↗Pradeep Ravikumar ↗

arXiv:2606.18509v1 Announce Type: new Abstract: Reliable generalization in conditional latent variable models requires understanding both identifiability and extrapolation: how observed variation across attributes determines latent structure, and how that structure determines distributions at unseen attributes. However, existing identifiability and extrapolation guarantees are largely model-specific, with separate analyses in nonlinear ICA, causal representation learning, perturbation modeling, and related conditional latent variable models. We introduce concept modulation models (CMMs), an attribute-indexed class of conditional generative models with structure $A\to \Lambda \to C\to X$, where attributes select modulators, modulators induce latent concept laws, and concepts generate observed features. CMMs lift transition-based identifiability to conditional settings by showing that feature agreement on observed attributes induces a latent concept transition constrained by the CMM class. We express these constraints through attribute potentials, log-density ratios between attribute-conditioned concept laws, separating the generic lifting step from model-specific rigidity arguments. The same potentials control extrapolation: agreement at unseen attributes holds exactly when the transported attribute-potential identities extend to those attributes. This yields algebraic extrapolation criteria, identifies the common potential-based proof objects behind several existing identifiability and extrapolation results, and, when combined with the model-specific rigidity arguments in those works, recovers their stated conclusions.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.07591

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

作者:

Wanghan Xu ↗Shuo Li ↗Tianlin Ye ↗Qinglong Cao ↗Yixin Chen ↗Hengjian Gao ↗Yiheng Wang ↗Qi Li ↗Kun Li ↗Sheng Xu ↗Shengdu Chai ↗Fangchen Yu ↗…

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2605.16713

GeoWorld-VLM: Geometry from World Models for Vision-Language Models

作者:

Renjie Gu ↗Kaichen Zhou ↗Yan Luo ↗Mengyu Wang ↗

Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between. One cause of this failure arises before language reasoning begins: the visual pathway may compress or discard critical 3D structural cues during feature extraction, so the language model receives image representations that are already insufficient for reliable spatial judgment. We introduce GeoWorld-VLM, a VLM-side distillation framework that transfers geometric structure from frozen camera-conditioned video world models into VLMs. GeoWorld-VLM fine-tunes only the image encoder and multimodal projector, aligning post-projector image features with intermediate world-model representations while leaving the main backbone frozen. Given images, a prompt, and a sampled camera trajectory, the world-model teacher converts static visual input into a synthetic multi-view spatial signal. Training combines spatial answer supervision, teacher-student feature alignment, and a preservation anchor to the original VLM. Since the language model remains frozen, GeoWorld-VLM preserves the original model's linguistic capabilities while attributing spatial improvements to the enhanced visual pathway. To evaluate the effectiveness and generality of the proposed method, we apply GeoWorld-VLM to two distinct VLM architectures and observe consistent improvements across both backbones. GeoWorld-VLM improves performance by approximately 4 percent on both the What'sUp and VSR benchmarks, suggesting that world-model-guided visual alignment generalizes across model structures and spatial reasoning datasets.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.18203

RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills

作者:

Weizhi Zhang ↗Zechen Li ↗Hamid Palangi ↗Ben Graef ↗A. Ali Heydari ↗Simon A. Lee ↗Salman Rahman ↗Ray Luo ↗Zeinab Esmaeilpour ↗Erik Schenck ↗Chloe Zhang ↗Yamin Li ↗…

The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access. However, large-scale clinical deployment remains constrained by an open-ended evaluation bottleneck: physician annotation is reliable but costly and unscalable, while LLM-as-a-judge evaluators are scalable but subjective, inconsistent, and sometimes clinically misaligned. We introduce RubricsTree, a scalable evaluation framework with an expert-aligned hierarchical taxonomy of over 100 atomic, clinically-verifiable Boolean rubrics, evolving from the insights of 4,000 real user queries through an iterative human-in-the-loop curation protocol with an expertise panel led by an experienced physician. A context-aware adaptive router activates only the relevant auto-weighted rubric subset per query, providing the throughput needed for scalable evaluation with expert-aligned quality. Through a systematic meta-evaluation, we show that RubricsTree (i) substantially exceeds a strong large-scale evaluation baseline in expert alignment on challenging open-ended queries; (ii) reliably penalizes contextually degraded responses; and (iii) when used as structured instructions, text feedback, or training rewards for performance optimization, yields up to ~66% relative gains on HealthBench for Gemini, GPT, and Qwen model families. RubricsTree thus provides a scalable, auditable, and evolving evaluation infrastructure required for the continuous optimization of product-level personal healthcare AI.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13044

No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions

作者:

Xu Yang ↗Zhizhou Sha ↗Junbo Li ↗Jian Yu ↗Yifan Sun ↗Matthew Zhao ↗Jinrui Fang ↗Xinyue Guo ↗Yining Wu ↗Xu Hu ↗Yifu Luo ↗Qiang Liu ↗…

As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such as hidden instructions and prompt injection. We study a harder and more policy-relevant failure mode: no hidden text, no prompt injection, and no changes to methods, experiments, figures, equations, proofs, or numerical results. The attacker modifies only presentation-level content, such as the abstract, contribution framing, related work, discussion, and narrative structure. We introduce adversarial repackaging: a closed-loop attack that uses AI-reviewer feedback to search for presentation-level revisions while keeping the scientific evidence fixed. Across three mainstream AI reviewers, adversarial repackaging achieves a 75.1% attack success rate and a mean score gain of +1.21/10. The effect is not explained by ordinary prose polishing. We also reveal that strategies that change how the reviewer interprets the paper, such as related-work repositioning and analytical discussion expansion, substantially outperform surface edits such as local polishing, table formatting, and algorithm boxes. Our analysis reveals two deeper structural failure modes. First, AI reviewers are easier to impress than to convince: highlighting strengths reliably increases perceived merit, while attempts to dissolve weaknesses frequently backfire. Second, AI reviewers can confuse the appearance of addressing a limitation with actually resolving it, allowing unchanged evidence to be reinterpreted as stronger scientific contribution. These results show that the deployment risk is not only malicious hidden instructions, but the emergence of paper presentation itself as an optimization surface. We release a contamination-free rolling benchmark and attack framework for testing whether AI reviewers remain anchored to scientific content under presentation-only edits.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.12670

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

作者:

Xiangyi Li ↗Yimin Liu ↗Wenbo Chen ↗Bingran You ↗Zonglin Di ↗Yifeng He ↗Shenghan Zheng ↗Kyoung Whan Choe ↗Jiankai Sun ↗Shuyi Wang ↗Chujun Tao ↗Binxu Li ↗…

arXiv:2602.12670v4 Announce Type: replace Abstract: Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2603.10444

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

作者:

Hengjie Cao ↗Zhendong Huang ↗Mengyi Chen ↗Yifeng Yang ↗Fang Dong ↗Anrui Chen ↗Ruijun Huang ↗Xin Zhang ↗Mingzhi Dong ↗Yujiang Wang ↗Jinlong Hou ↗Qin Lv ↗…

arXiv:2603.10444v2 Announce Type: replace-cross Abstract: FP4 training promises substantial memory and compute savings for large language models, but remains fragile because blockwise quantization is dictated by extreme activation magnitudes, which inflate dynamic range and compress long-tail signals. We identify a counterintuitive source of this failure: dominant activation outliers are not merely arbitrary sparse events, but are largely induced by a coherent rank-one mean bias, whose direction aligns with the leading anisotropic spectral component. This mean component strengthens during training, is amplified and reshaped by attention and FFN operators, and increasingly dominates top activation magnitudes. Crucially, this discovery reveals that a seemingly complex outlier-suppression problem admits a truly simple solution: isolate the coherent mean before quantization. We therefore propose Averis, a mean-residual splitting quantization method that separates the mean component using only reductions and elementwise subtractions before FP4 quantization. Across Qwen3 0.6B Dense trained on 100B tokens and Qwen3 7B A1.5B MoE trained on 50B tokens, Averis enables robust W4A4G4 FP4 training, reducing BF16 loss gaps to 1.19%/0.81% versus 2.05%/1.10% for NVIDIA's recently released Hadamard-based outlier-smoothing method, while limiting downstream gaps to 0.89/0.71 points. With only 2.20% end-to-end overhead over vanilla NVFP4, about 30% of NVIDIA's Hadamard-based design, Averis provides a hardware-efficient path to stable low-bit LLM training. Complementary to Hadamard, Averis further reduces the Qwen3-0.6B loss and downstream gaps to 0.94% and 0.73 points when combined. Code is available at: https://anonymous.4open.science/r/averis-504D.

阅读与讨论 → 访问原文 →

19.

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 →

20.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11556

Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices

作者:

arXiv:2606.11556v1 Announce Type: cross Abstract: Continuous electrocardiography (ECG) monitoring could surface rhythm abnormalities before they escalate into cardiovascular events. However, a deployable system must satisfy three requirements simultaneously: legal-grade privacy (GDPR, HIPAA), real-time inference on constrained edge hardware, and detection quality under non-IID cross-hospital data. We design and evaluate an end-to-end federated system addressing all three for unsupervised 12-lead ECG anomaly detection on PTB-XL dataset, combining three autoencoder families (VanillaAE, ConvAE, VAE), Flower-based federated averaging (FedAvg) across ten simulated hospitals, client-side differentially private SGD (DP-SGD) with a Rényi-DP accountant, and 8-bit integer (INT8) post-training quantization with Raspberry Pi 4 benchmarking. Our main contributions are: an empirical characterization of how these mechanisms compose, practical DP-specific recommendations, and technical and security insights for a clinically sensitive setting. Federated learning matches or exceeds the centralized baseline across all architectures (ConvAE federated area under the ROC curve, AUROC, $0.782$), and an $\varepsilon$ sweep identifies $\varepsilon=4$ as the recommended clinical operating point. INT8 quantization roughly halves model size and cuts Pi 4 latency by up to $44%$ with $

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14218

Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback

作者:

Litian Liang ↗Jingxi Xu ↗Xinda Qi ↗Yujun Cai ↗Houzhu Ding ↗Luqi Wang ↗Zhixin Sun ↗Jyh-Herng Chow ↗Ming Yang ↗Mark Cutkosky ↗

arXiv:2606.14218v1 Announce Type: cross Abstract: For robots to work safely in household environments, they need to be compliant and react to torque and force feedback during contact. However, the majority of existing data collection pipelines still lack the ability to capture force and torque data for learning active compliant policies. In this paper, we present Universal Manipulation Exoskeleton (UME), an upper-limb exoskeleton that provides real-time haptic torque feedback while recording whole-arm configurations and joint torque signals for teleoperation. With transparent torque feedback, human operators can even unsheathe kinematically constrained objects while blindfolded. UME is low-cost, lightweight, and portable. Equipped with an embedded IMU, it enables teleoperation for mobile manipulation. With our proposed universal retargeting algorithm, UME can teleoperate a range of robots, including the 7DoF OpenArm, 7DoF Franka, and 6DoF X-ARM. We demonstrate that this combination of capabilities enables learning bimanual, whole-body, and active compliant policies that operate effectively in highly constrained spaces. The learned robust autonomous policies achieve high success rates across a variety of tasks, including long-horizon mobile manipulation, force-mediated box flipping, visually occluded box pushing, and space-constrained tabletop manipulation. Videos, code, and additional information can be found at https://ume-exo.github.io.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2509.20241

Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling

作者:

Felipe Oviedo ↗Fiodar Kazhamiaka ↗Esha Choukse ↗Allen Kim ↗Amy Luers ↗Melanie Nakagawa ↗Ricardo Bianchini ↗Juan M. Lavista Ferres ↗

arXiv:2509.20241v2 Announce Type: replace Abstract: As AI inference scales to billions of queries, estimates of per-query energy use are increasingly important for capacity planning, efficiency interventions, and policy. Yet many public estimates assume non-production settings, leading to systematic overestimation. We introduce a bottom-up framework estimating inference energy from token throughput, node power, and overhead under large-scale deployment assumptions. For frontier-scale models (>200B parameters) on H100 nodes, we estimate a median energy of 0.31 Wh/query (IQR 0.16-0.60), indicating widely cited estimates are overstated by 4-20x. In test-time scaling scenarios 15x longer than typical queries, the median energy rises 13x to 3.91 Wh (IQR 2.15-7.05). Across models, serving systems, and hardware, we estimate 8-20x line-of-sight energy reductions. At datacenter scale, serving 1 billion queries/day requires 0.7 GWh; if 10% are long queries, demand rises to 1.7 GWh/day. With efficiency interventions, it falls to 0.8 GWh/day, mitigating the energy impact of test-time scaling.

阅读与讨论 → 访问原文 →

23.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2602.24006

Fulde-Ferrell superfluids in an asymmetric three-component Fermi Gas

作者:

Yuhan Lu ↗Lihong Zhou ↗Yongping Zhang ↗

arXiv:2602.24006v2 Announce Type: replace-cross Abstract: An asymmetric three-component Fermi gas, featuring Raman-induced spin-orbit coupling between the first and second components and contact interaction only between the first and third components, introduces both spin-orbit coupling and population imbalance-two mechanisms known to stabilize the Fulde-Ferrell superfluids.We systematically study Fulde-Ferrell superfluids in an asymmetric three-component Fermi gas { in two dimensions and at zero temperature} by finding the global minima of the thermodynamic potential. We reveal a new class of composite Fulde-Ferrell superfluids that emerges when strong spin-orbit coupling generates a double-well structure in momentum space within the lower spin-orbit-coupled band. The key features of these composite superfluids are identified.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15301

Discovering Lattice Reduction Strategies via Self-Play

作者:

Mohamed Malhou ↗Kristin Lauter ↗Ludovic Perret ↗

arXiv:2606.15301v1 Announce Type: cross Abstract: The Lenstra-Lenstra-Lovász (LLL) algorithm is a seminal contribution to computer science used for lattice basis reduction, yet its polynomial-time outputs produce bases that are far from optimal as the dimension grows. We show that deep reinforcement learning can discover strictly superior, generalizable reduction strategies by interacting with the primitive action space of LLL. We formulate lattice reduction as a single-player Markov Decision Process (MDP) and train a deep residual network using an AlphaZero-style self-play pipeline augmented with adaptive-horizon MCTS (Monte Carlo Tree Search), which couples multi-step network predictions with an entropy-gated expansion mechanism. The resulting policy, DeltaStar, is trained exclusively on small $8$-dimensional $q$-ary lattices and requires fewer primitive row operations than LLL. Crucially, it generalizes zero-shot to unseen moduli and higher dimensions up to $n=32$ without retraining.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.20515

S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence

作者:

Yalun Dai ↗Hao Li ↗Shulin Tian ↗Runmao Yao ↗Yuhao Dong ↗Fangzhou Hong ↗Zhaoxi Chen ↗Fangfu Liu ↗Baoliang Tian ↗Dingwen Zhang ↗Tao Wang ↗Kim-Hui Yap ↗…

Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inference from isolated visual observations. We introduce \textsc{S-Agent}, a spatial tool-use agentic paradigm for understanding and reasoning over continuous multi-view images and videos. By formulating spatial reasoning as spatio-temporal evidence accumulation rather than isolated frame-level prediction, \textsc{S-Agent} reshapes spatial perception into scene-centric understanding beyond frame-centric recognition. Specifically, \textsc{S-Agent} casts the VLM as a semantic planner that decides what evidence is needed, while a hierarchy of spatial tools and experts grounds objects in 2D, lifts them into 3D geometric evidence, and aggregates this evidence into high-level spatial knowledge (e.g., counting, measurement, orientation, and relative position). Additionally, a temporal memory mechanism, including Scene Memory for maintaining the evolving scene state and Agent Memory for accumulating reasoning context, enables evidence integration across frames and reasoning steps. Comprehensive experiments on multi-view and video spatial reasoning benchmarks show that \textsc{S-Agent} consistently improves both open-source and closed-source VLMs in a training-free manner. Beyond inference-time augmentation, supervised fine-tuning (SFT) on \textsc{S-Agent}-generated spatial trajectories \textsc{S-300K} yields \textsc{S-Agent-8B}, a compact spatial agent that significantly surpasses similar-scale baselines (e.g., Qwen3-VL-8B) and performs comparably to advanced closed-source models (e.g., GPT-5.4 and Gemini 3).

阅读与讨论 → 访问原文 →

探索全球前沿学术脉络