CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs

Rotary Positional Embedding (RoPE) is a key component of context scaling in Large Language Models (LLMs). While various methods have been proposed to adapt RoPE to longer contexts, their guiding principles generally fall into two categories: (1) out-of-distribution (OOD) mitigation, which scales RoPE frequencies to accommodate unseen positions, and (2) Semantic Modeling, which posits that the attention scores computed with RoPE should always prioritize semantically similar tokens. In this work, we unify these seemingly distinct objectives through a minimalist intervention, namely CoPE: soft clipping lowfrequency components of RoPE. CoPE not only eliminates OOD outliers and refines semantic signals, but also prevents spectral leakage caused by hard clipping. Extensive experiments demonstrate that simply applying our soft clipping strategy to RoPE yields significant performance gains that scale up to 256k context length, validating our theoretical analysis and establishing CoPE as a new state-of-the-art for length generalization. Our code, data, and models are available at https://github.com/hrlics/CoPE.

Mitigating Hallucination in Financial Retrieval-Augmented Generation via Fine-Grained Knowledge Verification

In financial Retrieval-Augmented Generation (RAG) systems, models frequently rely on retrieved documents to generate accurate responses due to the time-sensitive nature of the financial domain. While retrieved documents help address knowledge gaps, model-generated responses still suffer from hallucinations that contradict the retrieved information. To mitigate this inconsistency, we propose a Reinforcement Learning framework enhanced with Fine-grained Knowledge Verification (RLFKV). Our method decomposes financial responses into atomic knowledge units and assesses the correctness of each unit to compute the fine-grained faithful reward. This reward offers more precise optimization signals, thereby improving alignment with the retrieved documents. Additionally, to prevent reward hacking (e.g., overly concise replies), we incorporate an informativeness reward that encourages the policy model to retain at least as many knowledge units as the base model. Experiments conducted on the public Financial Data Description (FDD) task and our newly proposed FDD-ANT dataset demonstrate consistent improvements, confirming the effectiveness of our approach.

VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents

This work presents VTok, a unified video tokenization framework that can be used for both generation and understanding tasks. Unlike the leading vision-language systems that tokenize videos through a naive frame-sampling strategy, we propose to decouple the spatial and temporal representations of videos by retaining the spatial features of a single key frame while encoding each subsequent frame into a single residual token, achieving compact yet expressive video tokenization. Our experiments suggest that VTok effectively reduces the complexity of video representation from the product of frame count and per-frame token count to their sum, while the residual tokens sufficiently capture viewpoint and motion changes relative to the key frame. Extensive evaluations demonstrate the efficacy and efficiency of VTok: it achieves notably higher performance on a range of video understanding and text-to-video generation benchmarks compared with baselines using naive tokenization, all with shorter token sequences per video (e.g., 3.4% higher accuracy on our TV-Align benchmark and 1.9% higher VBench score). Remarkably, VTok produces more coherent motion and stronger guidance following in text-to-video generation, owing to its more consistent temporal encoding. We hope VTok can serve as a standardized video tokenization paradigm for future research in video understanding and generation.

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane

Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When adapted to vision transformers, the standard axial formulation decomposes two-dimensional spatial positions into horizontal and vertical components, implicitly restricting positional encoding to axis-aligned directions. We identify this directional constraint as a fundamental limitation of the standard axial 2D RoPE, which hinders the modeling of oblique spatial relationships that naturally exist in natural images. To overcome this limitation, we propose Spiral RoPE, a simple yet effective extension that enables multi-directional positional encoding by partitioning embedding channels into multiple groups associated with uniformly distributed directions. Each group is rotated according to the projection of the patch position onto its corresponding direction, allowing spatial relationships to be encoded beyond the horizontal and vertical axes. Across a wide range of vision tasks including classification, segmentation, and generation, Spiral RoPE consistently improves performance. Qualitative analysis of attention maps further show that Spiral RoPE exhibits more concentrated activations on semantically relevant objects and better respects local object boundaries, highlighting the importance of multi-directional positional encoding in vision transformers.

Kimi K2.5: Visual Agentic Intelligence

We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to $4.5\times$ over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.

A Generalist Foundation Model for Total-body PET/CT Enables Diagnostic Reporting and System-wide Metabolic Profiling

Total-body PET/CT enables system-wide molecular imaging, but heterogeneous anatomical and metabolic signals, approximately 2 m axial coverage, and structured radiology semantics challenge existing medical AI models that assume single-modality inputs, localized fields of view, and coarse image-text alignment. We introduce SDF-HOLO (Systemic Dual-stream Fusion Holo Model), a multimodal foundation model for holistic total-body PET/CT, pre-trained on more than 10,000 patients. SDF-HOLO decouples CT and PET representation learning with dual-stream encoders and couples them through a cross-modal interaction module, allowing anatomical context to refine PET aggregation while metabolic saliency guides subtle morphological reasoning. To model long-range dependencies across the body, hierarchical context modeling combines efficient local windows with global attention. To bridge voxels and clinical language, we use anatomical segmentation masks as explicit semantic anchors and perform voxel-mask-text alignment during pre-training. Across tumor segmentation, low-dose lesion detection, and multilingual diagnostic report generation, SDF-HOLO outperforms strong task-specific and clinical-reference baselines while reducing localization errors and hallucinated findings. Beyond focal interpretation, the model enables system-wide metabolic profiling and reveals tumor-associated fingerprints of inter-organ metabolic network interactions, providing a scalable computational foundation for total-body PET/CT diagnostics and system-level precision oncology.

SRAW-Attack: Space-Reweighted Adversarial Warping Attack for SAR Target Recognition

Synthetic aperture radar (SAR) imagery exhibits intrinsic information sparsity due to its unique electromagnetic scattering mechanism. Despite the widespread adoption of deep neural network (DNN)-based SAR automatic target recognition (SAR-ATR) systems, they remain vulnerable to adversarial examples and tend to over-rely on background regions, leading to degraded adversarial robustness. Existing adversarial attacks for SAR-ATR often require visually perceptible distortions to achieve effective performance, thereby necessitating an attack method that balances effectiveness and stealthiness. In this paper, a novel attack method termed Space-Reweighted Adversarial Warping (SRAW) is proposed, which generates adversarial examples through optimized spatial deformation with reweighted budgets across foreground and background regions. Extensive experiments demonstrate that SRAW significantly degrades the performance of state-of-the-art SAR-ATR models and consistently outperforms existing methods in terms of imperceptibility and adversarial transferability. Code is made available at https://github.com/boremycin/SAR-ATR-TransAttack.

GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning

The evolution of Remote Sensing Vision-Language Models(RS-VLMs) emphasizes the importance of transitioning from perception-centric recognition toward high-level deductive reasoning to enhance cognitive reliability in complex spatial tasks. However, current models often suffer from logical hallucinations, where correct answers are derived from flawed reasoning chains or rely on positional shortcuts rather than spatial logic. This decoupling undermines reliability in strategic spatial decision-making. To address this, we present GeoReason, a framework designed to synchronize internal thinking with final decisions. We first construct GeoReason-Bench, a logic-driven dataset containing 4,000 reasoning trajectories synthesized from geometric primitives and expert knowledge. We then formulate a two-stage training strategy: (1) Supervised Knowledge Initialization to equip the model with reasoning syntax and domain expertise, and (2) Consistency-Aware Reinforcement Learning to refine deductive reliability. This second stage integrates a novel Logical Consistency Reward, which penalizes logical drift via an option permutation strategy to anchor decisions in verifiable reasoning traces. Experimental results demonstrate that our framework significantly enhances the cognitive reliability and interpretability of RS-VLMs, achieving state-of-the-art performance compared to other advanced methods.

SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection

Multimodal object detection leveraging RGB and Infrared (IR) images is pivotal for robust perception in all-weather scenarios. While recent adapter-based approaches efficiently transfer RGB-pretrained foundation models to this task, they often prioritize model efficiency at the expense of cross-modal structural consistency. Consequently, critical structural cues are frequently lost when significant domain gaps arise, such as in high-contrast or nighttime environments. Moreover, conventional static multimodal fusion mechanisms typically lack environmental awareness, resulting in suboptimal adaptation and constrained detection performance under complex, dynamic scene variations. To address these limitations, we propose SLGNet, a parameter-efficient framework that synergizes hierarchical structural priors and language-guided modulation within a frozen Vision Transformer (ViT)-based foundation model. Specifically, we design a Structure-Aware Adapter to extract hierarchical structural representations from both modalities and dynamically inject them into the ViT to compensate for structural degradation inherent in ViT-based backbones. Furthermore, we propose a Language-Guided Modulation module that exploits VLM-driven structured captions to dynamically recalibrate visual features, thereby endowing the model with robust environmental awareness. Extensive experiments on the LLVIP, FLIR, KAIST, and DroneVehicle datasets demonstrate that SLGNet establishes new state-of-the-art performance. Notably, on the LLVIP benchmark, our method achieves an mAP of 66.1, while reducing trainable parameters by approximately 87% compared to traditional full fine-tuning. This confirms SLGNet as a robust and efficient solution for multimodal perception.

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

In this paper, we propose NeoVerse, a versatile 4D world model that is capable of 4D reconstruction, novel-trajectory video generation, and rich downstream applications. We first identify a common limitation of scalability in current 4D world modeling methods, caused either by expensive and specialized multi-view 4D data or by cumbersome training pre-processing. In contrast, our NeoVerse is built upon a core philosophy that makes the full pipeline scalable to diverse in-the-wild monocular videos. Specifically, NeoVerse features pose-free feed-forward 4D reconstruction, online monocular degradation pattern simulation, and other well-aligned techniques. These designs empower NeoVerse with versatility and generalization to various domains. Meanwhile, NeoVerse achieves state-of-the-art performance in standard reconstruction and generation benchmarks. Our project page is available at https://neoverse-4d.github.io