中 EN
登录 注册账户
×

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
作者: Chen Kang ×
↻ 换一批
01.
arXiv (CS.CV) 2026-06-17

NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Results

作者:
Zheng Chen↗Zongwei Wu↗Eduard Zamfir↗Kai Zhang↗Yulun Zhang↗Radu Timofte↗Xiaokang Yang↗Hongyuan Yu↗Cheng Wan↗Yuxin Hong↗Zhijuan Huang↗Yajun Zou↗…

This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CV) 2026-06-18

DreamReg: Belief-Driven World Model for 2D-3D Ultrasound Registration

作者:
Luoyao Kang↗Yuelin Zhang↗Jiwei Shan↗Haifan Gong↗Qingpeng Ding↗Shing Shin Cheng↗

Ultrasound (US) is widely used for surgical navigation, yet real-time registration between intraoperative 2D slices and preoperative 3D volumes remains challenging due to partial observability, speckle noise, and the action-dependent US acquisition. Existing methods are one-shot or short-horizon, making it hard for them to gather evidence over time or capture how surgeons adjust probe motion based on on-screen feedback. We propose DreamReg, a belief-driven world-model framework that formulates 2D-3D registration as belief updating over rigid transformations. DreamReg maintains a latent belief state that summarizes past observations and poses information, and continuously refines the transformation through learned dynamics as new slices arrive. During training, DreamReg is exposed to probe-motion trajectories that mimic clinical scanning behavior and learns to update its belief by conditioning pose refinement on the current US observation. During inference, DreamReg refines registration via internal imagination: it rolls out the learned world model to simulate candidate probe motions and their predicted observations, and integrates these imagined outcomes to converge to an accurate rigid transformation. Experiments on CAMUS and u-RegPro datasets demonstrate improved robustness and competitive registration accuracy for real-time guidance compared with state-of-the-art methods.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-19

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 →
04.
arXiv (CS.CV) 2026-06-16

V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos

作者:
Kaihan Chen↗Yanming Shao↗Haifeng Ji↗Xiaokang Yang↗Yao Mu↗

Achieving autonomous robotic dexterous manipulation requires precise, human-like action sequences at scale. As a scalable supplement to costly teleoperation data, extracting trajectories with both visual fidelity and physical plausibility from monocular videos represents a promising frontier in embodied AI. To this end, we introduce V2P-Manip, an efficient framework designed to learn dexterous manipulation policies directly from human demonstration videos. We establish an efficient, integrated pipeline encompassing 3D asset acquisition, trajectory estimation, and dexterous policy learning. To bridge the gap between visual perception and physical constraints, we introduce a two-stage refinement process to enforce spatial alignment and physical consistency. Evaluations on the TACO and OakInk benchmarks demonstrate that our approach significantly outperforms previous methods in pose accuracy, adaptability to unstructured environments, and training efficiency. Ultimately, experimental results confirm an average success rate of over 75% across multiple synthetic manipulation tasks and validate the adaptability of the extracted manipulation priors across diverse dexterous hand embodiments.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-15

ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation

作者:
Dongdong Nian↗Dongqi Fu↗Chenliang Xu↗Yinglong Xia↗Hong Li↗Hong Yan↗Jian Kang↗

arXiv:2606.14260v1 Announce Type: cross Abstract: Semantic IDs are crucial in generative recommendation, but with a fundamental limitation: temporal information is not well incorporated into semantic IDs. Instead, time influences recommendation only implicitly (e.g., through session construction heuristics, preference alignment, or sequence order), while existing semantic ID learning remains entirely time-agnostic. This design conflates interactions occurring under distinct temporal contexts into identical semantic representations, implicitly assuming that item semantics and user intent are temporally stationary. Such an assumption is misaligned with real-world recommendation scenarios, where evolving interaction rhythms play a central role. In this work, we investigate where and how the explicit time should be incorporated into semantic ID for generative recommendation. First, we systematically characterize the design space along three orthogonal dimensions of temporal signals and present a unified framework, ChronoID, for time-aware semantic ID learning. Then, by contributing a new time-explicit generation recommendation benchmark, ChronoID answers the questions: what is the effective way of infusing time, how to design the architecture, and where does the gain come from.

阅读与讨论 → 访问原文 →
06.
arXiv (CS.CL) 2026-06-12

Zero-source LLM Hallucination Detection with Human-like Criteria Probing

作者:
Jiahao Yang↗Shuhai Zhang↗Hailong Kang↗Feng Liu↗Qi Chen↗Mingkui Tan↗

Large language models (LLMs) often hallucinate by generating factually incorrect or unfaithful content, posing significant risks to their safe use. Detecting such hallucinations is particularly challenging under the zero-source constraint, where no model internals or external references are available, and detection must rely solely on the textual query-answer pair. In this paper, we propose Human-like Criteria Probing for Hallucination Detection (HCPD), a paradigm that emulates the multi-faceted reasoning of human evaluators. Its core is a Human-like Criteria Probing (HCP) mechanism, in which a LLM agent adaptively decomposes its judgment into a weighted set of interpretable criteria and aggregates criterion-specific scores into a final truthfulness measure. To achieve this adaptive capability, we introduce a reward-based alignment scheme using only weak supervision from semantic consistency. At inference, we employ a multi-sampling aggregation strategy to ensure robust decisions while preserving full interpretability. We further provide theoretical analysis supporting the reliability of our approach. Extensive experiments show that HCPD consistently outperforms state-of-the-art baselines, offering an effective and explainable solution for zero-source hallucination detection. Code is available at https://github.com/TRISKEL10N/HCPD.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-16

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 →
08.
arXiv (CS.CL) 2026-06-15

Decoupled Mixture-of-Experts for Parametric Knowledge Injection

作者:
Baoqing Yue↗Weihang Su↗Qingyao Ai↗Yichen Tang↗Changyue Wang↗Jiacheng Kang↗Jingtao Zhan↗Yiqun Liu↗

Knowledge injection aims to equip large language models (LLMs) with external, domain-specific, or time-sensitive knowledge. Existing approaches typically face a trade-off between flexibility and integration: retrieval-augmented generation keeps knowledge outside the model but only provides prompt-level augmentation, whereas post-training based methods encode new knowledge into shared parameters but may introduce catastrophic forgetting, knowledge conflict, and costly updates. In this paper, we propose Decoupled Mixture-of-Experts (DMoE), a modular architecture for parametric knowledge injection that decouples both experts and the router from the base model. DMoE converts external knowledge corpora into independently updatable expert modules and uses a lightweight uncertainty-aware router to activate relevant experts only when the base model lacks sufficient knowledge during generation. To support efficient auto-regressive inference, DMoE attaches experts only to the final-layer feed-forward network, preserving KV-cache reuse while enabling parameter-level knowledge augmentation. Experiments on knowledge-intensive benchmarks show that DMoE consistently improves answer quality over retrieval and adapter-based baselines.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.AI) 2026-06-16

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

作者:
Jialei Chen↗Kai Wang↗Kang Chen↗Shuaihang Chen↗Feng Gao↗Wenhao Tang↗Zhiyuan Li↗Weilin Liu↗Zhuyu Yao↗Boxun Li↗Yuanbo Xu↗Chao Yu↗…

arXiv:2606.15768v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene. World-Action Models (WAMs) address this limitation by conditioning policies on predicted futures, yet existing approaches typically rely on computationally expensive video generation with substantial pixel-level redundancy. We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video. At the core of LaWAM is a latent-action-conditioned Latent World Model (LaWM). We obtain LaWM by training a latent action model in the latent space of a pretrained vision foundation model and repurposing its forward decoder to predict future observation features for scene evolution. LaWAM then conditions action generation on these predicted latent visual subgoals to enable dynamics-aware robot control. LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference. LaWAM runs in 187 ms per action-chunk prediction and achieves up to 24x lower wall-clock latency than pixel-space WAMs.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.CL) 2026-06-18

Enhancing Multilingual Reasoning via Steerable Model Merging

作者:
Zhuoran Li↗Rui Xu↗Jian Yang↗Junnan Liu↗Zhijun Chen↗Qianren Mao↗Hongcheng Guo↗Jiaheng Liu↗Likang Xiao↗Ming Li↗Xiaojie Wang↗

Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model. It has achieved promising generalization in multilingual reasoning tasks by aligning feature spaces of different models. However, the merged single model often fails to address the conflicts between source models, leading to suboptimal performance. In other words, the one-size-fits-all merging strategy may not align with the characteristics of different inputs which may require prioritizing certain models over others. To this end, we propose a Steerable Model Merging (ST-Merge) framework to modulate the contribution of each source model. To realize this idea, we introduce a gated cross-attention mechanism to weight or filter the two attended source models in an adaptive manner. Extensive experiments demonstrate that ST-Merge consistently outperforms multiple strong baselines on four multilingual reasoning benchmarks across 21 different languages.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-16

SDFLoRA: Selective Decoupled Federated LoRA for Privacy-preserving Fine-tuning with Heterogeneous Clients

作者:
Zhikang Shen↗Jianrong Lu↗Haiyuan Wan↗Jianhai Chen↗

arXiv:2601.11219v3 Announce Type: replace-cross Abstract: Federated learning (FL) for large language models (LLMs) has attracted increasing attention as a privacy-preserving approach for adapting models over distributed data, where parameter-efficient methods such as Low-Rank Adaptation (LoRA) are widely adopted to reduce communication and memory costs. However, practical deployments often exhibit rank and data heterogeneity: clients operate under different low-rank budgets and data distributions, making direct aggregation of LoRA updates biased and unstable. Existing approaches either enforce a unified rank or align heterogeneous updates into a single shared subspace, which tends to mix transferable and client-specific directions and consequently undermines personalization. Moreover, under differential privacy (DP), perturbing such structurally mixed updates injects noise into directions that should remain purely local, leading to unnecessary utility degradation. To address these issues, we propose Selective Decoupled Federated LoRA (SDFLoRA), a structure-aware LoRA framework that decouples each client update into a shared component for aggregation and a private component that preserves client-specific semantics. Only the shared component participates in subspace alignment, while the private component remains local and uncommunicated, making the training DP-compatible and stabilizing aggregation under rank heterogeneity. By injecting noise only into the aggregated shareable update, this approach avoids perturbations to local directions and improves the utility-privacy trade-off. Experiments on multiple benchmarks demonstrate that SDFLoRA outperforms federated LoRA baselines and achieves a strong utility-privacy trade-off.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.CL) 2026-06-11

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

作者:
Yi Liu↗Zhihao Chen↗Yanjun Zhang↗Gelei Deng↗Yuekang Li↗Jianting Ning↗Leo Yu Zhang↗

LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges. Community registries have emerged to distribute these skills, but the security implications remain unstudied due to the absence of labeled threat data. This paper presents a systematic security analysis of 98,380 skills collected from two major registries. Through a combination of static pattern matching and dynamic behavioral verification, we identify 157 skills exhibiting confirmed malicious behavior, encompassing 632 distinct vulnerabilities across 13 attack techniques. Our analysis reveals that these threats are deliberate rather than accidental: each malicious skill contains an average of 4.03 vulnerabilities spanning multiple attack phases. We identify two dominant attack strategies with statistically significant negative correlation – credential theft via remote code execution, and agent manipulation through adversarial instructions embedded in documentation. Over half of all confirmed cases originate from a single threat actor employing templated brand impersonation at scale. We further observe that attack sophistication correlates with concealment investment, with advanced skills universally employing undocumented capabilities while also exploiting platform-native trust mechanisms. Following responsible disclosure, registry maintainers removed all 157 (100%) of the reported skills. Our dataset and detection pipeline are publicly available to facilitate future research on securing LLM agent ecosystems.

阅读与讨论 → 访问原文 →
13.
bioRxiv (Bioinfo) 2026-06-12

Deciphering cross-omics complexity of tissues via diagonal integration of unpaired spatial multi-omics data

作者:
Zhou↗Kangning↗Xiao↗Chen↗Zhang↗

Recent spatial multi-omics technologies enable the simultaneous in situ profiling of multiple omics modalities on the same tissue section; however, they face challenges in experimental complexity and high costs. This technical limitation can be circumvented by diagonal integration methods, which integrate omics data from different modalities. However, existing single-cell diagonal integration approaches overlook spatial information, causing unreliable anchoring across omics layers. Here, we introduce STAMO, a graph attention neural network model for spatially aware integration of unpaired spatial slices from different omics. Systematic benchmarking on spatial epigenome-transcriptome slices proves that STAMO outperforms the state-of-the-art methods in generating aligned embeddings and identifying consensus spatial domains across omics. We apply STAMO to integrate unpaired data from diverse spatial omics types (transcripts, epigenetics, DNA, and proteins), including slices from spatial RNA and four different epigenomic modalities, spatial ATAC and RNA slices across embryonic stages, spatial protein and RNA slices, and spatial DNA and RNA slices. In addition, the integration capability of STAMO can be further used to achieve cross-omics generation, offering a solution for exploring spatial region-specific gene regulatory mechanisms.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-12

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

作者:
Zihao Wang↗Yiming Li↗Yutong Wu↗Zheyu Liu↗Kangjie Chen↗Fok Kar Wai↗Pin-Yu Chen↗Vrizlynn L. L. Thing↗Bo Li↗Dacheng Tao↗Tianwei Zhang↗

arXiv:2606.13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences. This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour. Existing security benchmarks adopt an attack-centric perspective, focusing on the technical feasibility of injections while overlooking the nuanced distribution of resulting harms. In practice, however, prompt-injection risk is victim-dependent: a single exploit can produce asymmetric consequences for different stakeholders, and the same attack pattern may exhibit substantially different effectiveness depending on whom it targets. To capture these properties, we introduce \sysname, a stakeholder-centric benchmark to systematically categorize and attribute harm in real-world web agent systems. It distinguishes between affected entities (e.g., user, seller, platform), decomposes the attacks into concrete objectives, and evaluates each case with complementary outcome- and process-level metrics. Our results reveal substantial and heterogeneous vulnerabilities: not a single attack objective is reliably resisted by current agents, and failures distribute across qualitatively distinct modes ranging from stealthy parasitism (attack succeeds without disrupting the user's delegated task) to misaligned disruption (task disrupted without attack success) and compounded failure (both adversarial objective and task integrity simultaneously violated). These patterns are missed by conventional evaluation, highlighting the need for stakeholder-aware assessment of LLM-based agents in real-world deployments. Benchmark is available at https://github.com/StakeBench/SBC.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CL) 2026-06-16

Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift

作者:
Weihang Su↗Jiacheng Kang↗Jingyan Xu↗Qingyao Ai↗Jianming Long↗Hanwen Zhang↗Bangde Du↗Xinyuan Cao↗Min Zhang↗Yiqun Liu↗

Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate weight drift, potentially causing catastrophic forgetting and degrading general capabilities. Retrieval-augmented generation avoids such parameter drift, yet often lacks the depth of parametric knowledge integration. In this paper, we propose ReGrad (Retrievable Gradients), a new paradigm that treats gradients as retrievable units of knowledge. ReGrad pre-computes document-specific gradients offline, stores them in an indexed Gradient Bank, and retrieves only query-relevant gradients at inference time for temporary weight adaptation. However, raw language-modeling gradients are optimized for token-level document reconstruction rather than for query-driven knowledge use. We therefore introduce a bi-level meta-learning objective that reshapes document-derived gradients into generalizable adaptation signals for downstream tasks. Experiments across general and domain-specific settings show that \textsc{ReGrad} outperforms CPT and RAG baselines, enabling scalable and reversible parametric knowledge injection without accumulating weight drift.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-12

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization

作者:
Zhixiong Zhao↗Zukang Xu↗Zhixuan Chen↗Xing Hu↗Zhe Jiang↗Dawei Yang↗

arXiv:2606.13054v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization has emerged as a promising compression technique, offering significant reductions in model size and inference complexity. However, existing methods struggle with heavy-tailed activation distributions and therefore keep activations in high precision, fundamentally limiting end-to-end inference acceleration. To overcome this limitation, we propose TWLA, a post-training quantization (PTQ) framework that achieves 1.58-bit weight compression and 4-bit activation quantization while maintaining high accuracy. TWLA comprises three components: (1) Euclidean-to-Manifold Asymmetric Ternary Quantizer (E2M-ATQ) minimizes layer-output error under weight ternarization via a two-stage optimization from Euclidean initialization to manifold relocation; (2) Kronecker Orthogonal Tri-Modal Shaping (KOTMS) applies a Kronecker-structured orthogonal rotation to reshape weights into ternary-friendly tri-modal distributions, while the shared rotation statistically suppresses activation outliers; and (3) Inter-Layer Aware Activation Mixed Precision (ILA-AMP) explicitly introduces adjacent-layer second-order interaction costs in bit allocation and jointly optimizes for the layer-wise disparity of activation quantization gains induced by the shared orthogonal transform, preventing cascades triggered by a few weak layers. Extensive experiments demonstrate that TWLA maintains high accuracy under W1.58A4, while delivering significant inference acceleration. The code is available at .

阅读与讨论 → 访问原文 →
17.
arXiv (CS.CV) 2026-06-18

Cosmos 3: Omnimodal World Models for Physical AI

作者:
NVIDIA↗Aditi↗Niket Agarwal↗Arslan Ali↗Jon Allen↗Martin Antolini↗Adeline Aubame↗Alisson Azzolini↗Junjie Bai↗Maciej Bala↗Yogesh Balaji↗Josh Bapst↗…

We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configurations, Cosmos 3 seamlessly unifies critical modalities for Physical AI – effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework. Our evaluation demonstrates that Cosmos 3 establishes a new state-of-the-art across a diverse suite of understanding and generation tasks, demonstrating omnimodal world models as scalable, general-purpose backbones for embodied agents. Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written. To accelerate open research and deployment in Physical AI, we make our code, model checkpoints, curated synthetic datasets, and evaluation benchmark available under the Linux Foundation's OpenMDW-1.1 License at https://github.com/nvidia/cosmos and https://huggingface.co/collections/nvidia/cosmos3. The project website is available at https://research.nvidia.com/labs/cosmos-lab/cosmos3.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.CV) 2026-06-15

CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation

作者:
Sharath Girish↗Tsai-Shien Chen↗Zhikang Dong↗Mukesh Singhal↗Hao Chen↗Sergey Tulyakov↗Aliaksandr Siarohin↗

Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions. Together, these elements demand a level of fine-grained control beyond current text-to-video models. Existing work addresses each axis in isolation: multi-subject personalization, temporal control, multi-shot synthesis, or camera control; no prior framework jointly integrates all four. We present CineOrchestra, a unified video diffusion model that controls subjects, events, cameras, and shot transitions simultaneously. Our key insight is that these heterogeneous cinematic elements share a fundamental structure: each is an entity acting over a specific temporal interval, which can therefore all be expressed through one shared structure of entity-centric conditioning primitives, augmented with reference images for visual entities. This formulation reduces the architectural challenge to a single positional encoding problem, which we solve with two parameter-free coordinated rotary embeddings: (a) an interval-sampled temporal RoPE that yields consistent attention behavior across events of dramatically varying duration, and (b) a 2D entity-temporal cross-attention RoPE that disambiguates per-entity conditions and routes each to its corresponding spatiotemporal region. On two new benchmarks, CineOrchestra outperforms six per-axis specialists on dense caption following and shot-transition timing, with consistent gains in a pairwise user study and component ablations.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.CV) 2026-06-17

TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations

作者:
Zikang Xiong↗Weixin Li↗Zhouchonghao Wu↗Akshay Rangesh↗Saarth Bonde↗Grantland Hall↗Chen Tang↗Yihan Hu↗Wei Zhan↗

End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all stages: collecting and labeling millions of driving frames is costly, and closed-loop RL on images is bottlenecked by the per-step cost of photorealistic rendering plus a forward pass through a large vision backbone. Self-play in vectorized simulators changes the economics: millions of rollout steps per second, and a state distribution naturally rich in collisions, near-misses, and recoveries that no driving log contains. Our approach exploits this asymmetry by decoupling learning to drive from learning to see. We pretrain a single policy by self-play, then align its latent space with a pretrained vision backbone, through the action KL divergence and a batch-relational low-rank structural loss. The action target comes from the self-play policy, so alignment never supervises against a logged trajectory: a paired dataset of (image, scene-state) frames suffices, with no need for the curated expert demonstrations that imitation pretraining is built on. On photorealistic 3D Gaussian splatting closed-loop scenarios, the resulting end-to-end policy matches or exceeds prior end-to-end methods.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.CV) 2026-06-17

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

作者:
Yatai Ji↗An-Chieh Cheng↗Yang Fu↗Yukang Chen↗Han Zhang↗Zhaojing Yang↗Wei Huang↗Ka Chun Cheung↗Song Han↗Vidya Nariyambut Murali↗Pavlo Molchanov↗Jan Kautz↗…

Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging. Moreover, different spatial queries call for fundamentally different strategies: some are best addressed through purely linguistic, step-by-step deduction, while others require explicit 3D grounding before quantitative inference. We present Dual-Path Spatial Reasoning via Reinforcement Learning for Spatial VLMs (SR-REAL), a unified framework that equips a spatial VLM with two complementary reasoning paths: Language-Only Reasoning (LOR), which performs step-by-step linguistic deduction, and Detect-Then-Reason (DTR), which detects 3D geometric cues (e.g., centers or bounding boxes) via region tokens before explicit geometric inference. SR-REAL begins with a cold-start supervised fine-tuning stage that constructs LOR and DTR chain-of-thought supervision and exposes a region-to-3D interface, followed by RL that optimizes the policy model with accuracy and format rewards; for DTR, a discrete center-based detection reward further refines geometric alignment. Across diverse spatial benchmarks, SR-REAL significantly outperforms spatial VLM baselines: (i) a single RL-trained model supports both reasoning paths, with DTR excelling in region-aware tasks through precise 3D localization and LOR enhancing general spatial reasoning; (ii) jointly training both paths fosters mutual reinforcement; (iii) high-quality, blended cold-start data is crucial for stable RL optimization; and (iv) the model generalizes across datasets and domains without per-task tuning, demonstrating positive transfer between LOR and DTR.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CL) 2026-06-15

AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition

作者:
Jixuan Chen↗Jianzhi Shen↗Haoqiang Kang↗Zhi Hong↗Qingyi Jiang↗Soham Bose↗Yiming Zhang↗Leon Leng↗Amit Vyas↗Lingjun Mao↗Siru Ouyang↗Kun Zhou↗…

LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffolds often improve performance, they are often embedded in tightly coupled pipelines, making it difficult to isolate component contributions, compare alternative designs, or understand how module interactions shape agent behavior. We introduce AgentSpec, a modular specification framework that represents embodied agents as typed compositions of reusable policy components with standardized interfaces. AgentSpec standardizes the interfaces among perception, memory, reasoning, reflection, action, and optional learning, enabling components to be swapped and recombined under controlled conditions. We instantiate this framework across DeliveryBench, ALFRED, MiniGrid, and RoboTHOR, and analyze reasoning, memory, reflection, and reinforcement-learning modules across model backbones. Our results show that agent performance is governed by scaffold compatibility and interaction effects rather than isolated module strength. In particular, structured multi-granularity memory improves long-horizon state tracking, reasoning and memory interact non-uniformly across environments, reflection trades off correction and cost, and RL-trained policies compose best when optimized with deployment-time scaffold structure. AgentSpec provides a controlled foundation for studying, comparing, and designing composable LLM agents. Our code, baselines and interactive playground are publicly available at https://agentspec-embodied.github.io.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CV) 2026-06-19

HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining

作者:
Juncheng Ma↗Jianxin Bi↗Yufan Deng↗Xuanran Zhai↗Kewei Zhang↗Ye Huang↗Bo Liang↗Shukai Gong↗Jiankai Tu↗Xiaotian Tang↗Jiaxin Li↗Kaiqi Chen↗…

Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remain the dominant pretraining source due to their precise action supervision and embodiment alignment, yet their scalability is limited by high collection cost, acquisition difficulty, and low behavioral and environmental diversity. These limitations have sparked interest in egocentric human video as a scalable, substantially lower-cost, and more diverse alternative for embodied model pretraining. However, its effectiveness compared to teleoperated real-robot data remains underexplored. To address this question, we conduct a systematic study comparing egocentric human video and teleoperated real-robot trajectories as pretraining data sources for embodied foundation models, under fixed post-training and validation protocols. Surprisingly, we find that egocentric data, when processed through a carefully designed filtering and labeling pipeline, is not merely a viable substitute for model pretraining but can lead to superior performance. With the same amount of pretraining data, models pretrained on egocentric data achieve a 24% lower validation loss on real-robot action prediction, as well as 52.5% and 90% higher success rates on in-distribution and out-of-distribution real-robot task execution, respectively. This finding verifies a scalable paradigm for embodied foundation models: pretrain on egocentric human video to learn diverse world representations, then adapt with a small amount of labeled real-robot data for action-space alignment. We hope this study encourages broader exploration of egocentric data and offers guidance for data quality assessment before costly robot data collection.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CV) 2026-06-18

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

作者:
Kangsheng Duan↗Ziyang Xu↗Wenyu Liu↗Xiaohu Ruan↗Xiaoxin Chen↗Xinggang Wang↗

While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we propose Moebius, a highly efficient lightweight inpainting framework. We systematically reconstruct the diffusion backbone by introducing the Local-$\lambda$ Mix Interaction ($L\lambda MI$) block. Comprising Local-$\lambda$ and Interactive-$\lambda$ modules, it elegantly summarizes spatial contexts and global semantic priors into fixed-size linear matrices, preserving complex latent interactions while drastically shedding parameters. Furthermore, to unlock the full representational capacity of this highly compact architecture, we synergistically pair it with an adaptive multi-granularity distillation strategy. Operating strictly within the latent space to avoid expensive pixel-space decoding, this strategy dynamically balances multiple gradient-based losses to achieve high-fidelity alignment. Extensive experiments across natural and portrait benchmarks demonstrate that this optimal synergy enables Moebius to rival or even surpass the generation quality of the 10B-level industrial generalist FLUX.1-Fill-Dev. Remarkably, Moebius achieves this using less than 2\% of the parameters (0.22B vs. 11.9B) while delivering a $>15\times$ acceleration in total inference time, setting a new efficiency standard for high-fidelity inpainting. Project page at https://hustvl.github.io/Moebius.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CV) 2026-06-15

Planning with the Views via Scene Self-Exploration

作者:
Kangrui Wang↗Linjie Li↗Zhengyuan Yang↗Shiqi Chen↗Zihan Wang↗Li Fei-Fei↗Jiajun Wu↗Leonidas Guibas↗Lijuan Wang↗Manling Li↗

Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transforms the view, and (2)composing many such transformations across multi-turn plans to identify a target view. We probe both abilities in our proposed ViewSuite, a 3D point-cloud environment on real ScanNet scenes. Across 13 frontier VLMs, a critical planning gap emerges: they possess basic view-action knowledge but fail to compose it across multi-turn plans, with the gap widening as viewpoint distance grows. To close this gap, we propose an iterative framework that alternates self-exploration with view graph distillation. The key insight is that all exploration trajectories, regardless of their outcome, collectively form a view graph that compactly captures how viewpoints connect across a scene. Distilling this graph into diverse supervised tasks reshapes the policy distribution and overcomes the sparse rewards that stall pure RL. This improves Qwen2.5-VL-7B from 2.5% to 47.8% on interactive view planning, surpassing GPT-5.4 Pro (18.5%) and Gemini 3.1 Pro (21.4%). Self-exploration emerges as a promising path toward VLMs that can actively reason and plan in 3D space. Code and Data are at https://viewsuite.github.io.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.LG) 2026-06-19

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution

作者:
Mingyu Yang↗Keye Zheng↗Congchao Cheng↗Yujie Liu↗Xingkang Lu↗Fan Jiang↗Yefei Zheng↗

arXiv:2606.20475v1 Announce Type: new Abstract: In batch-style trace distillation, the same memory operation may receive contradictory feedback across different batches. Existing methods lack a cross-batch, operation-level evidence accumulation mechanism, making it impossible to distinguish stably effective operations from accidental hits. This paper formalizes the requirement as two structural conditions, alignability and comparability, and proposes Marginal Advantage Accumulation (MAA). MAA constructs differential signals to make them comparable across batches, accumulates signed evidence per operation via EMA, and ensures cross-batch traceability through semantic identity merging. As a post-processing architecture, MAA achieves the best results in 14 out of 16 settings across 4 benchmarks and 4 target models, consistently outperforming existing batch-level distillation baselines and matching or surpassing online alternatives in most settings, while reducing optimization-phase token consumption by approximately 75%.

阅读与讨论 → 访问原文 →