D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use

Effective tool use and reasoning are essential capabilities for large reasoning models~(LRMs) to address complex real-world problems. Through empirical analysis, we identify that current LRMs lack the capability of sub-task decomposition in complex tool use scenarios, leading to Lazy Reasoning. To address this, we propose a two-stage training framework D-CORE~(\underline{\textbf{D}}ecomposing tasks and \underline{\textbf{Co}}mposing \underline{\textbf{Re}}asoning processes) that first incentivize the LRMs' task decomposition reasoning capability via self-distillation, followed by diversity-aware reinforcement learning~(RL) to restore LRMs' reflective reasoning capability. D-CORE achieves robust tool-use improvements across diverse benchmarks and model scales. Experiments on BFCLv3 demonstrate superiority of our method: D-CORE-8B reaches 77.7\% accuracy, surpassing the best-performing 8B model by 5.7\%. Meanwhile, D-CORE-14B establishes a new state-of-the-art at 79.3\%, outperforming 70B models despite being 5$\times$ smaller. The source code is available at https://github.com/alibaba/EfficientAI.

EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis

Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate speech in text-to-speech (TTS) synthesis. However, many emotion-aware TTS systems, including large language model (LLM)-based designs, rely on scaling fixed emotion embeddings or external guidance, limiting their ability to model emotion-specific latent characteristics. To address this gap, we present EmoShift, a lightweight activation-steering framework incorporating a EmoSteer layer, which learns a steering vector for each target emotion in the output embedding space to capture its latent offset and maintain stable, appropriate expression across utterances and categories. With only 10M trainable parameters,less than 1/30 of full fine-tuning, EmoShift outperforms zero-shot and fully fine-tuned baselines in objective and subjective evaluations, enhancing emotional expressiveness while preserving naturalness and speaker similarity. Further analysis confirms the proposed EmoSteer layer's effectiveness and reveals its potential for controllable emotional intensity in speech synthesis.

A Survey of Pinching-Antenna Systems (PASS)

The pinching-antenna system (PASS), recently proposed as a flexible-antenna technology, has been regarded as a promising solution for several challenges in next-generation wireless networks. It provides large-scale antenna reconfiguration, establishes stable line-of-sight links, mitigates signal blockage, and exploits near-field advantages through its distinctive architecture. This article aims to present a comprehensive overview of the state of the art in PASS. The fundamental principles of PASS are first discussed, including its hardware architecture, circuit and physical models, and signal models. Several emerging PASS designs, such as segmented PASS (S-PASS), center-fed PASS (C-PASS), and multi-mode PASS (M-PASS), are subsequently introduced, and their design features are discussed. In addition, the properties and promising applications of PASS for wireless sensing are reviewed. On this basis, recent progress in the performance analysis of PASS for both communications and sensing is surveyed, and the performance gains achieved by PASS are highlighted. Existing research contributions in optimization and machine learning are also summarized, with the practical challenges of beamforming and resource allocation being identified in relation to the unique transmission structure and propagation characteristics of PASS. Finally, several variants of PASS are presented, and key implementation challenges that remain open for future study are discussed.

RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking

Review ranking is pivotal in e-commerce for prioritizing diagnostic and authentic feedback from the deluge of user-generated content. While large language models have improved semantic assessment, existing ranking paradigms face a persistent trade-off in long-context settings. Pointwise scoring is efficient but often fails to account for list-level interactions, leading to miscalibrated top-$k$ rankings. Listwise approaches can leverage global context, yet they are computationally expensive and become unstable as candidate lists grow. To address this, we propose Residual Listwise Preference Optimization (RLPO), which formulates ranking as listwise representation-level residual correction over a strong pointwise LLM scorer. RLPO first produces calibrated pointwise scores and item representations, then applies a lightweight encoder over the representations to predict listwise score residuals, avoiding full token-level listwise processing. We also introduce a large-scale benchmark for long-context review ranking with human verification. Experiments show RLPO improves NDCG@k over strong pointwise and listwise baselines and remains robust as list length increases.

Unified Personalized Understanding, Generating and Editing

Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-fits-all'' paradigm and struggle to model user-specific concepts (e.g., generate a photo of \texttt{<maeve>}) in a consistent and controllable manner. Existing personalization methods typically rely on external retrieval, which is inefficient and poorly integrated into unified multimodal pipelines. Recent personalized unified models introduce learnable soft prompts to encode concept information, yet they either couple understanding and generation or depend on complex multi-stage training, leading to cross-task interference and ultimately to fuzzy or misaligned personalized knowledge. We present \textbf{OmniPersona}, an end-to-end personalization framework for unified LMMs that, for the first time, integrates personalized understanding, generation, and image editing within a single architecture. OmniPersona introduces structurally decoupled concept tokens, allocating dedicated subspaces for different tasks to minimize interference, and incorporates an explicit knowledge replay mechanism that propagates personalized attribute knowledge across tasks, enabling consistent personalized behavior. To systematically evaluate unified personalization, we propose \textbf{\texttt{OmniPBench}}, extending the public UnifyBench concept set with personalized editing tasks and cross-task evaluation protocols integrating understanding, generation, and editing. Experimental results demonstrate that OmniPersona delivers competitive and robust performance across diverse personalization tasks. We hope OmniPersona will serve as a strong baseline and spur further research on controllable, unified personalization.

Stereo Audio Rendering for Personal Sound Zones Using a Binaural Spatially Adaptive Neural Network (BSANN)

A binaural rendering framework for personal sound zones (PSZs) is proposed to enable multiple head-tracked listeners to receive fully independent stereo audio programs. Current PSZ systems typically rely on monophonic rendering and therefore cannot control the left and right ears separately, which limits the quality and accuracy of spatial imaging. The proposed method employs a Binaural Spatially Adaptive Neural Network (BSANN) to generate ear-optimized loudspeaker filters that reconstruct the desired acoustic field at each ear of multiple listeners. The framework integrates anechoically measured loudspeaker frequency responses, analytically modeled transducer directivity, and rigid-sphere head-related transfer functions (HRTFs) to enhance acoustic accuracy and spatial rendering fidelity. An explicit active crosstalk cancellation (XTC) stage further improves three-dimensional spatial perception. Experiments show significant gains in measured objective performance metrics, including inter-zone isolation (IZI), inter-program isolation (IPI), and crosstalk cancellation (XTC), with log-frequency-weighted values of 10.23/10.03 dB (IZI), 11.11/9.16 dB (IPI), and 10.55/11.13 dB (XTC), respectively, over 100-20,000 Hz. The combined use of ear-wise control, accurate acoustic modeling, and integrated active XTC produces a unified rendering method that delivers greater isolation performance, increased robustness to room asymmetry, and more faithful spatial reproduction in real acoustic environments.

TEA: Temporal Adaptive Satellite Image Semantic Segmentation

Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable advancements in SITS segmentation with predetermined sequence lengths. However, we found that these approaches overlooked the generalization capability of models across scenarios with varying temporal length, leading to markedly poor segmentation results in such cases. To address this issue, we propose TEA, a TEmporal Adaptive SITS semantic segmentation method to enhance the model's resilience under varying sequence lengths. We introduce a teacher model that encapsulates the global sequence knowledge to guide a student model with adaptive temporal input lengths. Specifically, teacher shapes the student's feature space via intermediate embedding, prototypes and soft label perspectives to realize knowledge transfer, while dynamically aggregating student model to mitigate knowledge forgetting. Finally, we introduce full-sequence reconstruction as an auxiliary task to further enhance the quality of representations across inputs of varying temporal lengths. Through extensive experiments, we demonstrate that our method brings remarkable improvements across inputs of different temporal lengths on common benchmarks. Our code will be publicly available.

Envision: Embodied Visual Planning via Goal-Imagery Video Diffusion

Embodied visual planning aims to enable manipulation tasks by imagining how a scene evolves toward a desired goal and using the imagined trajectories to guide actions. Video diffusion models, through their image-to-video generation capability, provide a promising foundation for such visual imagination. However, existing approaches are largely forward predictive, generating trajectories conditioned on the initial observation without explicit goal modeling, thus often leading to spatial drift and goal misalignment. To address these challenges, we propose Envision, a diffusion-based framework that performs visual planning for embodied agents. By explicitly constraining the generation with a goal image, our method enforces physical plausibility and goal consistency throughout the generated trajectory. Specifically, Envision operates in two stages. First, a Goal Imagery Model identifies task-relevant regions, performs region-aware cross attention between the scene and the instruction, and synthesizes a coherent goal image that captures the desired outcome. Then, an Env-Goal Video Model, built upon a first-and-last-frame-conditioned video diffusion model (FL2V), interpolates between the initial observation and the goal image, producing smooth and physically plausible video trajectories that connect the start and goal states. Experiments on object manipulation and image editing benchmarks demonstrate that Envision achieves superior goal alignment, spatial consistency, and object preservation compared to baselines. The resulting visual plans can directly support downstream robotic planning and control, providing reliable guidance for embodied agents.

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Recent advances in pretraining general foundation models have significantly improved performance across diverse downstream tasks. While autoregressive (AR) generative models like GPT have revolutionized NLP, most visual generative pretraining methods still rely on BERT-style masked modeling, which often disregards the temporal information essential for video analysis. The few existing autoregressive visual pretraining methods suffer from issues such as inaccurate semantic localization and poor generation quality, leading to poor semantics. In this work, we propose NExT-Vid, a novel autoregressive visual generative pretraining framework that utilizes masked next-frame prediction to jointly model images and videos. NExT-Vid introduces a context-isolated autoregressive predictor to decouple semantic representation from target decoding, and a conditioned flow-matching decoder to enhance generation quality and diversity. Through context-isolated flow-matching pretraining, our approach achieves strong representations. Extensive experiments on large-scale pretrained models demonstrate that our proposed method consistently outperforms previous generative pretraining methods for visual representation learning via attentive probing in downstream classification.

Sum-Rate Maximization for Uplink Segmented Waveguide-Enabled Pinching-Antenna Systems

A multiuser uplink transmission framework based on the segmented waveguide-enabled pinching-antenna system (SWAN) is proposed under two operating protocols: segment selection (SS) and segment aggregation (SA). For each protocol, the achievable uplink sum-rate is characterized for both time-division multiple access (TDMA) and non-orthogonal multiple access (NOMA). Low-complexity placement methods for the pinching antennas (PAs) are developed for both protocols and for both multiple-access schemes. Numerical results validate the effectiveness of the proposed methods and show that SWAN achieves higher sum-rate performance than conventional pinching-antenna systems, while SA provides additional performance gains over SS.