Robotic task planning in real-world environments requires reasoning over implicit constraints from language and vision.

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking--enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and effective problem-solving. However, current single-agent work lacks a specialized design for acquiring meta-thinking, resulting in low efficacy. To address this challenge, we introduce Reinforced Meta-thinking Agents (ReMA), a novel framework that leverages Multi-Agent Reinforcement Learning (MARL) to elicit metathinking behaviors, encouraging LLMs to think about thinking.

Auditory attention detection (AAD) aims to decode listeners' focus in complex auditory environments from electroencephalography (EEG) recordings, which is crucial for developing neuro-steered hearing devices. Despite recent advancements, EEG-based AAD remains hindered by the absence of synergistic frameworks that can fully leverage complementary EEG features under energy-efficiency constraints. We propose S2M-Former, a novel spiking symmetric mixing framework to address this limitation through two key innovations: i) Presenting a spike-driven symmetric architecture composed of parallel spatial and frequency branches with mirrored modular design, leveraging biologically plausible token-channel mixers to enhance complementary learning across branches; ii) Introducing lightweight 1D token sequences to replace conventional 3D operations, reducing parameters by 14.7 . The brain-inspired spiking architecture further reduces power consumption, achieving a 5.8 energy reduction compared to recent ANN methods, while also surpassing existing SNN baselines in terms of parameter efficiency and performance. Comprehensive experiments on three AAD benchmarks (KUL, DTU and AV-GC-AAD) across three settings (within-trial, cross-trial and cross-subject) demonstrate that S2M-Former achieves comparable state-of-the-art (SOTA) decoding accuracy, making it a promising low-power, high-performance solution for AAD tasks.

Learning disentangled representations in sequential data is a key goal in deep learning, with broad applications in vision, audio, and time series. While realworld data involves multiple interacting semantic factors over time, prior work has mostly focused on simpler two-factor static and dynamic settings, primarily because such settings make data collection easier, thereby overlooking the inherently multifactor nature of real-world data. We introduce the first standardized benchmark for evaluating multi-factor sequential disentanglement across six diverse datasets spanning video, audio, and time series. Our benchmark includes modular tools for dataset integration, model development, and evaluation metrics tailored to multi-factor analysis. We additionally propose a post-hoc Latent Exploration Stage to automatically align latent dimensions with semantic factors, and introduce a Koopman-inspired model that achieves state-of-the-art results. Moreover, we show that Vision-Language Models can automate dataset annotation and serve as zeroshot disentanglement evaluators, removing the need for manual labels and human intervention. Together, these contributions provide a robust and scalable foundation for advancing multi-factor sequential disentanglement. Our code is available on GitHub, and the datasets and trained models are available on Hugging Face.

While large language models (LLMs) demonstrate strong reasoning capabilities utilizing reinforcement learning (RL) with verifiable reward, whether large visionlanguage models (VLMs) can directly inherit such capabilities through similar posttraining strategies remains underexplored. In this work, we conduct a systematic compositional probing study to evaluate whether current VLMs trained with RL or other post-training strategies can compose capabilities across modalities or tasks under out-of-distribution conditions. We design a suite of diagnostic tasks that train models on unimodal tasks or isolated reasoning skills, and evaluate them on multimodal, compositional variants requiring skill integration. Through comparisons between supervised fine-tuning (SFT) and RL-trained models, we identify three key findings: (1) RL-trained models consistently outperform SFT on compositional generalization, demonstrating better integration of learned skills; (2) although VLMs achieve strong performance on individual tasks, they struggle to generalize compositionally under cross-modal and cross-task scenarios, revealing a significant gap in current training strategies; (3) enforcing models to explicitly describe visual content before reasoning (e.g., caption-before-thinking), along with rewarding progressive vision-to-text grounding, yields notable gains. It highlights two essential ingredients for improving compositionality in VLMs: visual-to-text alignment and accurate visual grounding. Our findings shed light on the current limitations of RL-based reasoning VLM training and provide actionable insights toward building models that reason compositionally across modalities and tasks.

These authors contributed equally to this work.

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for training language models (LMs) on reasoning tasks that elicit emergent long chains of thought (CoTs).

Time-resolved single-cell omics data offers high-throughput, genome-wide measurements of cellular states, which are instrumental to reverse-engineer the processes underpinning cell fate. Such technologies are inherently destructive, allowing only cross-sectional measurements of the underlying stochastic dynamical system. Furthermore, cells may divide or die in addition to changing their molecular state. Collectively these present a major challenge to inferring realistic biophysical models. We present a novel approach, unbalanced probability flow inference, that addresses this challenge for biological processes modelled as stochastic dynamics with growth. By leveraging a Lagrangian formulation of the Fokker-Planck equation, our method accurately disentangles drift from intrinsic noise and growth.

Recently, deep learning-based pan-sharpening algorithms have achieved notable advancements over traditional methods. However, deep learning-based methods incur substantial computational overhead during inference, especially with large images. This excessive computational demand limits the applicability of these methods in real-world scenarios, particularly in the absence of dedicated computing devices such as GPUs and TPUs. To address these challenges, we propose Pan-LUT, a novel learnable look-up table (LUT) framework for pan-sharpening that strikes a balance between performance and computational efficiency for large remote sensing images. Our method makes it possible to process 15K 15K remote sensing images on a 24GBGPU. To finely control the spectral transformation, we devise the PAN-guided look-up table (PGLUT) for channel-wise spectral mapping. To effectively capture fine-grained spatial details, we introduce the spatial details look-up table (SDLUT).

Precise, generalizable subject-agnostic seizure prediction (SASP) remains a fundamental challenge due to the intrinsic complexity and significant spectral variability of electrophysiologial signals across individuals and recording modalities. We propose FAPEX, a novel architecture that introduces a learnable fractional neural frame operator (FrNFO) for adaptive time-frequency decomposition. Unlike conventional models that exhibit spectral bias toward low frequencies, our FrNFO employs fractional-order convolutions to capture both high and low-frequency dynamics, achieving approximately 10% improvement in F1-score and sensitivity over state-of-the-art baselines. The FrNFO enables the extraction of instantaneous phase and amplitude representations that are particularly informative for preictal biomarker discovery and enhance out-of-distribution generalization. FAPEXfurther integrates structural state-space modeling and channelwise attention, allowing it to handle heterogeneous electrode montages.