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: Tong Wei ×
↻ 换一批
01.
arXiv (CS.CV) 2026-06-15

IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products

作者:
Haonan Qi↗Jin Cao↗Yongqi Zhang↗Xintong Wang↗Weidong Tang↗Bin Chen↗Chengfu Huo↗Haojun Pan↗Hengyu You↗Jing Li↗Yingde Wang↗Liang Ding↗…

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction – recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86–94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15–34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CV) 2026-06-17

MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model

作者:
Lichen Bai↗Tianhao Zhang↗Shitong Shao↗Dingwei Tan↗Qiyu Zhong↗Zhengpeng Xie↗Haopeng Li↗Qinghao Huang↗Dandan Shen↗Tengjiao Ji↗Wei Wang↗Peicheng Wu↗…

As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but largely overlooked by previous studies. In this work, we define the position of social world models and build a prototype model as the first step towards this goal. While previous world models successfully simulate physical environments or gaming world exploration, they remain fundamentally detached from human-centric social dynamics. To bridge this gap as the first step to social world models, we present MaineCoon, the first real-time audio-visual autoregressive model that has 22B parameters and is capable of real-time streaming generation and sub-second interaction, with a record-breaking frame rate of up to 47.5 FPS, on a single GPU. To the best of our knowledge, MaineCoon is also the first real-time audio-visual generation model specifically optimized for social-interactive applications. To enable efficient and stable training, we introduce several novel techniques into MaineCoon, including self-resampling, cross-modal representation alignment, domain-aware preference optimization, and reinforced online-policy distillation (ROPD). We also design the first agentic streaming inference framework that supports thousand-second-scale or even longer generation while mitigating drift with agentic cache management and prompt planing. These innovations significantly accelerate training while optimizing real-time inference performance. We believe this work not only sets a new state-of-the-art (SOTA) performance benchmark for high-quality, low-latency, and long-horizon audio-visual autoregressive models, but also points out the paradigm shift desired for next-generation AI-native social platforms.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CV) 2026-06-17

Bridging Modality Disconnect in Self-Reflection via Closed-Loop Visually Grounded Verification

作者:
Haoyu Zhang↗Yuwei Wu↗Pengxiang Li↗Xintong Zhang↗Zhi Gao↗Rui Gao↗Mingyang Gao↗Che Sun↗Yunde Jia↗

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to hallucinations or logic errors. Existing VLMs often produce plausible yet ungrounded answers, and even when prompted to "reflect", their corrections may remain detached from the image evidence. To address this, we propose the MIRROR framework for Multimodal Iterative Reasoning via Reflection On visual Regions. By embedding visual reflection as a core mechanism, MIRROR is formulated as a closed-loop process comprising draft, critique, region-based verification, and revision, which are repeated until the output is visually grounded. To facilitate training of this model, we construct **ReflectV**, a visual reflective dataset for multi-turn supervision that explicitly contains reflection triggers, region-based verification actions, and answer revision grounded in visual evidence. Experiments on both general vision-language benchmarks and representative vision-language reasoning benchmarks show that MIRROR improves correctness and reduces visual hallucinations, demonstrating the value of training reflection as an evidence-seeking, region-aware verification process rather than a purely textual revision step.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CV) 2026-06-16

EyeMVP: OCT-Informed Fundus Representation Learning via Paired CFP–OCT Pretraining

作者:
Zhuo Deng↗Ruiheng Zhang↗Ziheng Zhang↗Weihao Gao↗Yitong Li↗Qian Wang↗Lei Shao↗Jiaoyue Dong↗Zhixi Zeng↗Lijian Fang↗Haibo Wang↗Xiaobin Lin↗…

Color fundus photography (CFP) is the mainstay for large-scale retinal screening, yet its diagnostic capacity is constrained by the lack of depth-resolved structural information. Optical coherence tomography (OCT) provides cross-sectional retinal anatomy, but is less accessible in population-level screening. Here, we present EyeMVP, a cross-modal retinal foundation model that uses paired CFP–OCT pretraining to learn OCT-informed CFP representations. EyeMVP is pretrained on 674,893 strict same-eye same-day paired CFP–OCT image triples from 112,642 patients across eight hospitals in China. The model uses cross-modal masked reconstruction to enrich CFP representations with OCT-associated supervision, while requiring only CFP images at inference. To accommodate the non-aligned imaging geometry between en-face CFP and cross-sectional OCT, EyeMVP combines source-constrained cross-attention with CFP-derived structural masks. Across 16 downstream tasks, including classification, segmentation, few-shot adaptation, and cross-modal retrieval, EyeMVP outperforms representative retinal foundation models and shows consistent gains on tasks involving macular and optic nerve structure. For CFP-challenging macular diseases, EyeMVP achieves an AUROC of 0.948 for macular edema (vs.~0.852 for EyeCLIP) and 0.825 for myopic macular schisis. In an exploratory reader study, EyeMVP exceeds junior and intermediate ophthalmologist groups but does not reach senior ophthalmologist performance on macular edema, while showing numerically higher balanced accuracy than all reader groups on myopic macular schisis. These results suggest that pixel-level cross-modal reconstruction can enrich CFP representations with OCT-associated supervision, providing a practical route toward stronger CFP-based retinal analysis in screening settings.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.LG) 2026-06-19

Multimodal Concept Bottleneck Models

作者:
Tongqing Shi↗Ge Yan↗Tuomas Oikarinen↗Tsui-Wei Weng↗

arXiv:2606.19882v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) enhance the interpretability of deep learning networks by aligning the features extracted from images with natural concepts. However, existing CBMs are constrained in their ability to generalize beyond a fixed set of predefined classes and the risk of non-concept information leakage, where predictive signals outside the intended concepts are inadvertently exploited. In this paper, we propose Multimodal Concept Bottleneck Model (MM-CBM) to address these issues and extend CBMs into CLIP. MM-CBM utilizes dual Concept Bottleneck Layers (CBLs) to align both the image and text embeddings into interpretable features. This allows us to perform new vision tasks like zero-shot classification or image retrieval in an interpretable way. Compared to existing methods, MM-CBM achieves up to 51.26% accuracy improvement on average across four standard benchmarks. Our method maintains high accuracy, staying within ~5% of black-box performance while offering greater interpretability.

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

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

作者:
Shuai Yang↗Bingjie Gao↗Ziwei Liu↗Jiaqi Wang↗Dahua Lin↗Tong Wu↗

Consistent video generation under editing operations requires persistence: when edits modify scene appearance or layout, subsequent generations should remain coherent across time and viewpoints. However, existing memory designs struggle to maintain long-term consistency after such modifications, as stored contexts may become outdated or invalid. To address this, we propose PermaVid, a novel framework built upon a multi-modal context memory that disentangles spatial context into semantic appearance and geometric structure, together with an edit-aware memory update and retrieval strategy that keeps memory evolution aligned with subsequent observations. Specifically, we develop two complementary memory banks: an RGB context memory that captures appearance-aware observations while implicitly encoding geometry, and a depth context memory that preserves geometry-only structure disentangled from semantics. Building on this design, we introduce a memory-guided video generation model that performs multi-modal feature fusion under reference conditions drawn from mixed-modality memory contexts. Experiments demonstrate that our method maintains strong long-term semantic and structural consistency after edits, significantly outperforming state-of-the-art methods.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-11

Learning Object Manipulation from Scratch via Contrastive Interaction

作者:
Tongle Shen↗Caleb Chuck↗Fan Feng↗Biwei Huang↗

arXiv:2606.11525v1 Announce Type: cross Abstract: Contrastive Reinforcement Learning (CRL) has seen recent success in a wide variety of goal-conditioned robotics tasks by learning structured representations of the dynamics. However, despite its success in locomotion and simpler control domains, CRL often struggles in interaction-rich manipulation. We argue that a key source of this difficulty is object-centric interaction, such as contact or grasping, that induces distinct changes in the underlying dynamic modes. In this work, we formulate manipulation dynamics as a piecewise-smooth Markov process and show that interaction-induced mode changes create piecewise nonlinear reachability structures that are difficult for standard CRL energy functions to represent and plan over. Based on this analysis, we introduce Interaction-weighted Resampling (IWR). IWR performs interaction-aware resampling around phases before, during, and after interactions, encouraging the learned representation to preserve the mode boundaries that determine future reachability to capture multi-modal and piecewise nonlinear reachability. Across interaction-centric environments, including 2D dynamic control, robotic manipulation, and robot air hockey, IWR improves both sample efficiency and overall performance over prior CRL methods, with 19.8% average improvement in simulation. Finally, using a sim-to-real pipeline with policies trained by IWR, we demonstrate the first real-world goal-conditioned robot air hockey agent capable of hitting goals, improving success from 25% to 60%. Project Page: IWR-arxiv.github.io.

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

ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation

作者:
Jingqi Zhou↗Sheng Wang↗Dezhao Deng↗Junwen Lu↗Junwei Su↗Qintong Li↗Jiahui Gao↗Hao Wu↗Jiyue Jiang↗Lingpeng Kong↗Dunhong Jin↗Chuan Wu↗…

arXiv:2602.07883v4 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between domain-specific performance and cross-task generalization: strong priors and compact tool spaces aid specialization but weaken transfer, while task-agnostic workflows and broad action spaces expand coverage but dilute guidance. Existing pre-execution optimization, planner-worker orchestration, and configuration patching fall short of resolving this tension, as they decouple adaptation from execution, causing information loss, fragmented optimization, and ambiguous credit assignment. We propose ToolSelf, a tool-driven runtime self-reconfiguration paradigm that abstracts configuration updates as a standardized tool interface and unifies execution and adaptation within one policy's action space. The execution agent can dynamically update sub-goals, strategies, toolboxes, context, and context-management modes based on task progress and feedback. We further introduce Configuration-Aware Two-stage Training (CAT), which combines rejection sampling fine-tuning with trajectory-level KTO reinforcement learning to internalize self-reconfiguration. Across diverse benchmarks, zero-shot ToolSelf rivals task-specialized agents; after CAT training, ToolSelf gains 28.8 points over the static-configuration baseline on average, illuminating a path toward emergent adaptivity that obviates manually injected guidance. The code is available at https://github.com/lian-tian-mo-zun/ToolSelf.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.LG) 2026-06-11

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

作者:
Haoyuan Deng↗Yitong Gao↗Yudong Lin↗Haichao Liu↗Zhenyu Wu↗Ziwei Wang↗

arXiv:2606.12372v1 Announce Type: cross Abstract: Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance. However, current HiL-RL frameworks remain intervention-intensive, relying on frequent human corrections to redirect the policy out of unproductive exploration, which incurs high labor cost and limits real-world scalability. To address this, we propose UniIntervene, an agentic intervention model that detects unproductive exploration and autonomously recovers the policy toward high-value states, taking over the bulk of interventions from human operators. Specifically, UniIntervene first performs future-conditioned action-value estimation, predicting the latent consequence of the current action and evaluating its induced value, which provides a more stable progress signal. Building on this, a temporal value-risk critic aggregates recent value dynamics and triggers intervention when the estimated value exhibits sustained stagnation or degradation. When intervention is required, UniIntervene retrieves a high-value recovery target from a memory of past intervention episodes and produces executable corrective actions through a goal-conditioned recovery policy. In this way, UniIntervene turns intervention from passive human correction into a value-aware recovery process for efficient real-world RL. Extensive experiments on diverse real-world manipulation tasks demonstrate that UniIntervene improves the average success rate by 8.6% while reducing human interventions by 57% relative to state-of-the-art HiL-RL baselines.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.CV) 2026-06-15

Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency

作者:
Zhitong Cheng↗Yiran Jiang↗Yulong Ge↗Yufeng Li↗Zhongheng Qin↗Rongzhi Lin↗Jianwei Ma↗

Domain shift, characterized by degraded model performance during transition from labeled source domains to unlabeled target domains, poses a persistent challenge for deploying deep learning systems. Current unsupervised domain adaptation (UDA) methods predominantly rely on fine-tuning feature extractors - an approach limited by inefficiency, reduced interpretability, and poor scalability to modern architectures. Our analysis reveals that models pretrained on large-scale data exhibit domain-invariant geometric patterns in their feature space, characterized by intra-class clustering and inter-class separation, thereby preserving transferable discriminative structures. These findings indicate that domain shifts primarily manifest as boundary misalignment rather than feature degradation. Unlike fine-tuning entire pre-trained models - which risks introducing unpredictable feature distortions - we propose the Feature-space Planes Searcher (FPS): a novel domain adaptation framework that optimizes decision boundaries by leveraging these geometric patterns while keeping the feature encoder frozen. This streamlined approach enables interpretative analysis of adaptation while substantially reducing memory and computational costs through offline feature extraction, permitting full-dataset optimization in a single computation cycle. Evaluations on public benchmarks demonstrate that FPS achieves competitive or superior performance to state-of-the-art methods. FPS scales efficiently with multimodal large models and shows versatility across diverse domains including protein structure prediction, remote sensing classification, and earthquake detection. We anticipate FPS will provide a simple, effective, and generalizable paradigm for transfer learning, particularly in domain adaptation tasks. .

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

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation

作者:
Bo Ye↗Xinyu Cui↗Jian Zhao↗Tong Wei↗Min-Ling Zhang↗

Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps early frames cached even when the current visual state has substantially diverged from them, while discarding potentially more relevant intermediate history. As a result, the retained long-range context may become less adaptive and bias generation toward outdated cues; in severe cases, RoPE-induced phase re-alignment can homogenize inter-head attention and cause sink collapse, where content regresses toward sink frames. We propose DySink, a retrieval-based framework that maintains a compact memory bank and selects visually relevant historical frames as dynamic frame sinks. DySink couples adaptive retrieval with a sink anomaly gate, which detects excessive inter-head consensus over retrieved context and suppresses collapse-prone context. Experiments on minute-long videos show that DySink consistently improves dynamic degree over strong baselines while also achieving higher temporal quality. The code and model weights will be released at https://github.com/yebo0216best/DySink.

阅读与讨论 → 访问原文 →
13.
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 →
14.
arXiv (CS.CV) 2026-06-11

DeceptionX: Explainable Deception Detection with Multimodal Large Language Models

作者:
Jiayu Zhang↗Shuo Ye↗Jiajian Huang↗Yawen Cui↗Taorui Wang↗Wei Xia↗Zeheng Wang↗Haowen Tang↗Hui Ma↗Zitong Yu↗

Deception detection is a critical and highly challenging task within affective computing and behavioral analysis. Existing deep learning methods typically treat this task as a straightforward classification problem; however, this black-box approach lacks interpretability and fails to capture the complex logical deduction processes utilized by human experts when identifying lies. While Multimodal Large Language Models (MLLMs) have shown potential, applying them effectively requires a bridge between low-level audiovisual cues and high-level logical reasoning. In this paper, we propose DeceptionX, a novel MLLM framework that shifts the paradigm of deception detection from black-box classification to an interpretable Observe-Think-Summarize reasoning process. To address the scarcity of high-quality reasoning data, we first constructed DeceptChain, a high-quality dataset developed through a human-in-the-loop process. This dataset synthesizes fine-grained visual and auditory evidence (such as micro-expressions and vocal tremors) into structured chain-of-thought reasoning data. Furthermore, we propose a three-stage training pipeline and a Discrepancy-Aware Redundancy Elimination~(DARE) strategy for DeceptionX to further enhance the model's generalization capabilities. Extensive experiments demonstrate that DeceptionX not only outperforms existing MLLM baselines and state-of-the-art methods on standard real-world benchmarks but also provides transparent, expert-level reasoning paths, bridging the critical gap between accuracy and interpretability in multimodal deception detection.

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

Depth-Attention: Cross-Layer Value Mixing for Language Models

作者:
Boyi Zeng↗Yiqin Hao↗Zitong Wang↗Shixiang Song↗He Li↗Feichen Song↗Yifan Liu↗Ziwei He↗Xinbing Wang↗Zhouhan Lin↗

Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference–a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends over the keys of earlier layers at the same token position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache–the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

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

CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering

作者:
Jie Hu↗Shengnan Wang↗Yutong He↗Ping Gong↗Jiawei Yi↗Juncheng Zhang↗Youhui Bai↗Renhai Chen↗Gong Zhang↗Cheng Li↗Kun Yuan↗

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges. Existing approaches either discard potentially critical information needed for future generations or offer limited efficiency gains due to high computational overhead. In this paper, we introduce CentroidKV, a simple yet effective framework for online KV cache clustering. Our approach is based on the observation that key states exhibit high similarity along the sequence dimension. To enable efficient clustering, we divide the sequence into chunks and propose Chunked Soft Matching, which employs an alternating partition strategy within each chunk and identifies clusters based on similarity. CentroidKV then merges the KV cache within each cluster into a single centroid. Additionally, we provide a theoretical analysis of the computational complexity and the optimality of the intra-chunk partitioning strategy. Extensive experiments across various models and long-context benchmarks demonstrate that CentroidKV achieves up to 75% reduction in KV cache memory usage while maintaining comparable model performance. Moreover, with minimal computational overhead, CentroidKV accelerates the decoding stage of inference by up to $1.92\times$ and increases the serving throughput by up to $4\times$.

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

Looped World Models

作者:
Hongyuan Adam Lu↗Z. L. Victor Wei↗Qun Zhang↗Jinrui Zeng↗Bowen Cao↗Lingwei Meng↗Mocheng Li↗Zezhong Wang↗Haonan Yin↗Naifu Xue↗Minyu Chen↗Cenyuan Zhang↗…

Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding errors. We resolve this by introducing Looped World Models (LoopWM), which are the first looped architectures for world modelling. Our method iteratively refines latent environment states through a parameter-shared transformer block. This yield up to 100x parameter efficiency over conventional approaches with adaptive computation that automatically scales depth to match the complexity of each prediction step. Orthogonal to scaling model size and training data, LoopWM establishes iterative latent depth as a new scaling axis for world simulation, which might significantly push the community forward.

阅读与讨论 → 访问原文 →
18.
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 →
19.
arXiv (CS.CV) 2026-06-16

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 →
20.
arXiv (CS.AI) 2026-06-16

MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis

作者:
Yuqi Zhan↗Xinyue Wu↗Tianyu Lin↗Yutong Bao↗Xiaoyu Wang↗Weihao Cheng↗Huangwei Chen↗Feiwei Qin↗Zhu Zhu↗

arXiv:2603.01131v3 Announce Type: replace-cross Abstract: Clinical diagnosis is a gradual process of evidence integration, in which physicians move from symptoms and medical history to examinations, competing hypotheses, disease relations, and treatment decisions. Large language models have advanced medical text understanding and generation. Yet their clinical use remains limited by weak evidence grounding, opaque reasoning, and inconsistent links among differential diagnosis, final diagnosis, diagnostic basis, and treatment planning. We introduce MedCollab, a multi-agent framework for full-cycle clinical diagnosis and report generation. MedCollab coordinates specialist and examination agents according to patient records. It structures agent deliberation with an Issue-Based Information System (IBIS) protocol, so that each diagnostic position is supported by patient-specific evidence and medical knowledge. It also builds Hierarchical Disease Relation Chains (HDRC) to connect accepted hypotheses through progression, complication, and comorbidity relations. During multi-round deliberation, a verifier-guided consensus module evaluates evidence support, medical plausibility, and logical conflicts. It then adjusts agent contributions and filters unsupported reasoning. Experiments on ClinicalBench and MIMIC-IV show that MedCollab outperforms leading LLMs and medical multi-agent baselines in diagnostic accuracy, evidence consistency, and clinical reasoning quality. These results indicate that structured and auditable collaboration can produce more faithful and clinically coherent diagnostic reports.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-19

Playful Agentic Robot Learning

作者:
Junyi Zhang↗Jiaxin Ge↗Hanjun Yoo↗Letian Fu↗Zihan Yang↗Yaowei Liu↗Raj Saravanan↗Shaofeng Yin↗Justin Yu↗Dantong Niu↗Zirui Wang↗Roei Herzig↗…

arXiv:2606.19419v1 Announce Type: cross Abstract: Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.AI) 2026-06-17

Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection

作者:
Runang He↗Tongya Zheng↗Huiling Peng↗Yuanyu Wan↗Bingde Hu↗Jiawei Chen↗Canghong Jin↗Mingli Song↗Can Wang↗

arXiv:2605.29526v2 Announce Type: replace-cross Abstract: Ever-evolving transaction patterns have significantly hindered anomaly detection on emerging cryptocurrency blockchains due to the vast number of addresses and diverse anomalous behaviors. Recently, advanced Graph Anomaly Detection (GAD) approaches applied to blockchains have faced two critical challenges: adversarial pattern evolution by malicious actors and the out-of-distribution (OOD) problem caused by varied transaction semantics on blockchains. To address these challenges, we propose a novel framework termed TEmporal Motif-aware Graph Test-Time Adaptation (TEMG-TTA). First, we comprehensively capture the 3-node temporal motif distribution of each active address using an efficient computational mechanism, enabling downstream temporal motif-aware graph learning. Second, we design a simple yet effective test-time adaptation strategy to facilitate the sharing of common patterns between training and testing graphs. Extensive experiments on 5 real-world datasets demonstrate that our proposed TEMG-TTA outperforms state-of-the-art GAD approaches by an average of 54.88\%. A further case study on interpretable motif patterns reveals that TEMG-TTA explicitly characterizes the complex transaction patterns of anomalous addresses, thereby verifying the effectiveness of our technical designs. Our code is publicly available at https://github.com/LuoXishuang0712/TEMG-TTA/.

阅读与讨论 → 访问原文 →
23.
arXiv (CS.CV) 2026-06-15

SAFformer:Improving Spiking Transformer via Active Predictive Filtering

作者:
Zequan Xie↗Weiming Zeng↗Yunhua Chen↗Sichang Ling↗Tongyang Chen↗Jinsheng Xiao↗

Spiking Neural Networks (SNNs) offer notable advantages in biological plausibility and energy efficiency, making them promising candidates for building low-power Transformers. However, existing Spiking Transformers largely adhere to a passive reactive paradigm, which struggles to focus on task-relevant information and incurs substantial computational overhead when processing redundant visual data. To overcome this fundamental yet underexplored limitation, we propose SAFformer, a novel Spiking Transformer architecture based on an active predictive filtering paradigm. Inspired by the brain's predictive coding mechanism, SAFformer actively suppresses predictable signals and focuses on salient visual features. Extensive experiments show that SAFformer establishes new state-of-the-art performance on CIFAR-10/100 and CIFAR10-DVS. Remarkably, on ImageNet-1K, it achieves 80.44% Top-1 accuracy with only 26.58M parameters and an energy consumption of 5.88 mJ, demonstrating an exceptional balance between accuracy and efficiency.

阅读与讨论 → 访问原文 →
24.
arXiv (quant-ph) 2026-06-12

Quantum Otto engine powered by an anisotropic Heisenberg XYZ model under independent local magnetic fields

作者:
Meiru Li↗Maimaitiyiming Tusun↗Fang Zhao↗Hasiyatihan Abudoula↗Tongcheng Wei↗

arXiv:2606.12877v1 Announce Type: new Abstract: We study a quantum Otto heat engine whose working substance is an anisotropic two-qubit Heisenberg XYZ model. Independent local magnetic fields are used to control each spin individually. The influence of the longitudinal coupling, anisotropy, transverse coupling, and local fields on the net work output and efficiency is systematically examined. Reducing the longitudinal coupling is found to markedly improve both the maximum work and the peak efficiency. The engine performance reaches an optimum at a particular value of the anisotropy parameter. A local work analysis clarifies how work is produced during the cycle. Because of the asymmetric local fields and the intrinsic spin-spin interaction, the two qubits play markedly different thermodynamic roles; the interaction term itself contributes crucially to the total work. We further analyze the variation of quantum entanglement, quantified by concurrence, along the cycle. The results indicate that a pronounced change in entanglement between the hot and cold isomagnetic strokes is closely correlated with the efficiency enhancement. This work offers new insight into the operating principles and control of quantum Otto heat engines.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.CV) 2026-06-16

Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering

作者:
Luca Hagen↗Johanna P. M\"uller↗Weitong Zhang↗Mengyun Qiao↗Bernhard Kainz↗

Small vision-language models (2-8B) are well-suited for clinical deployment due to privacy constraints, limited connectivity, and low-latency requirements favouring on-device or on-premise inference. However, their limited capacity exacerbates the generation of plausible but incorrect outputs. We extend game-theoretic decoding, previously restricted to text-only, closed-ended NLP tasks, to vision-language models for open-ended Medical VQA. We introduce a semantically aware Wasserstein stopping criterion that replaces lexical order matching, enabling convergence based on semantic consensus among near-synonymous candidate answers and avoiding unnecessary iterations caused by clinically equivalent ranking swaps. On VQA-RAD and PathVQA, we obtain consistent, statistically significant improvements over greedy and discriminative baselines. On VQA-RAD, we improve Qwen3-VL-2B by +3.5 percentage points (p < 0.01), surpassing the greedy 4B model, with similar trends at larger scales. On PathVQA, Gemma-3-4B with BDG matches MedGemma-4B under greedy decoding despite no domain-specific fine-tuning. At accuracy parity with classic BDG, the Wasserstein criterion reduces average convergence iterations by approximately 20%, improving inference efficiency while preserving the game-theoretic equilibrium behaviour. Code is available at https://github.com/luca-hagen/ Wasserstein-BDG-medical-VQA.

阅读与讨论 → 访问原文 →