Exploring Cross-Modal Flows for Few-Shot Learning

Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alignment between image and text, they often require parameter-efficient fine-tuning (PEFT) for further adjustment. Today's PEFT methods (e.g., prompt tuning, LoRA-based, or adapter-based) always selectively fine-tune a subset of parameters, which can slightly adjust either visual or textual features, and avoid overfitting. In this paper, we are the first to highlight that all existing PEFT methods perform one-step adjustment. It is insufficient for complex (or difficult) datasets, where features of different modalities are highly entangled. To this end, we propose the first model-agnostic multi-step adjustment approach by learning a cross-modal velocity field: Flow Matching Alignment (FMA). Specifically, to ensure the correspondence between categories during training, we first utilize a fixed coupling strategy. Then, we propose a noise augmentation strategy to alleviate the data scarcity issue. Finally, we design an early-stopping solver, which terminates the transformation process earlier, improving both efficiency and accuracy. Compared with one-step PEFT methods, FMA has the multi-step rectification ability to achieve more precise and robust alignment. Extensive results have demonstrated that FMA can consistently yield significant performance gains across various benchmarks and backbones, particularly on challenging datasets.

Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control

Building agents that autonomously operate mobile devices has attracted increasing attention. While Vision-Language Models (VLMs) show promise, most existing approaches rely on direct state-to-action mappings, which lack structured reasoning and planning, and thus generalize poorly to novel tasks or unseen UI layouts. We introduce Hi-Agent, a trainable hierarchical vision-language agent for mobile control, featuring a high-level reasoning model and a low-level action model that are jointly optimized. For efficient training, we reformulate multi-step decision-making as a sequence of single-step subgoals and propose a foresight advantage function, which leverages execution feedback from the low-level model to guide high-level optimization. This design alleviates the path explosion issue encountered by Group Relative Policy Optimization (GRPO) in long-horizon tasks and enables stable, critic-free joint training. Hi-Agent achieves a new State-Of-The-Art (SOTA) 87.9% task success rate on the Android-in-the-Wild (AitW) benchmark, significantly outperforming prior methods across three paradigms: prompt-based (AppAgent: 17.7%), supervised (Filtered BC: 54.5%), and reinforcement learning-based (DigiRL: 71.9%). It also demonstrates competitive zero-shot generalization on the ScreenSpot-v2 benchmark. On the more challenging AndroidWorld benchmark, Hi-Agent also scales effectively with larger backbones, showing strong adaptability in high-complexity mobile control scenarios.

Learning an Image Editing Model without Image Editing Pairs

Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of input-target pairs. This is a critical bottleneck, as such naturally occurring pairs are hard to curate at scale. Current workarounds use synthetic training pairs that leverage the zero-shot capabilities of existing models. However, this can propagate and magnify the artifacts of the pretrained model into the final trained model. In this work, we present a new training paradigm that eliminates the need for paired data entirely. Our approach directly optimizes a few-step diffusion model by unrolling it during training and leveraging feedback from vision-language models (VLMs). For each input and editing instruction, the VLM evaluates if an edit follows the instruction and preserves unchanged content, providing direct gradients for end-to-end optimization. To ensure visual fidelity, we incorporate distribution matching loss (DMD), which constrains generated images to remain within the image manifold learned by pretrained models. We evaluate our method on standard benchmarks and include an extensive ablation study. Without any paired data, our method performs on par with various image editing diffusion models trained on extensive supervised paired data, under the few-step setting. Given the same VLM as the reward model, we also outperform RL-based techniques like Flow-GRPO.

ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning

Reinforcement learning (RL) algorithms are highly sensitive to reward function specification, which remains a central challenge limiting their broad applicability. We present ARM-FM: Automated Reward Machines via Foundation Models, a framework for automated, compositional reward design in RL that leverages the high-level reasoning capabilities of foundation models (FMs). Reward machines (RMs) -- an automata-based formalism for reward specification -- are used as the mechanism for RL objective specification, and are automatically constructed via the use of FMs. The structured formalism of RMs yields effective task decompositions, while the use of FMs enables objective specifications in natural language. Concretely, we (i) use FMs to automatically generate RMs from natural language specifications; (ii) associate language embeddings with each RM automata-state to enable generalization across tasks; and (iii) provide empirical evidence of ARM-FM's effectiveness in a diverse suite of challenging environments, including evidence of zero-shot generalization.

ViTacGen: Robotic Pushing with Vision-to-Touch Generation

Robotic pushing is a fundamental manipulation task that requires tactile feedback to capture subtle contact forces and dynamics between the end-effector and the object. However, real tactile sensors often face hardware limitations such as high costs and fragility, and deployment challenges involving calibration and variations between different sensors, while vision-only policies struggle with satisfactory performance. Inspired by humans' ability to infer tactile states from vision, we propose ViTacGen, a novel robot manipulation framework designed for visual robotic pushing with vision-to-touch generation in reinforcement learning to eliminate the reliance on high-resolution real tactile sensors, enabling effective zero-shot deployment on visual-only robotic systems. Specifically, ViTacGen consists of an encoder-decoder vision-to-touch generation network that generates contact depth images, a standardized tactile representation, directly from visual image sequence, followed by a reinforcement learning policy that fuses visual-tactile data with contrastive learning based on visual and generated tactile observations. We validate the effectiveness of our approach in both simulation and real world experiments, demonstrating its superior performance and achieving a success rate of up to 86\%.

Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories

Abnormal stop detection (ASD) in intercity coach transportation is critical for ensuring passenger safety, operational reliability, and regulatory compliance. However, two key challenges hinder ASD effectiveness: sparse GPS trajectories, which obscure short or unauthorized stops, and limited labeled data, which restricts supervised learning. Existing methods often assume dense sampling or regular movement patterns, limiting their applicability. To address data sparsity, we propose a Sparsity-Aware Segmentation (SAS) method that adaptively defines segment boundaries based on local spatial-temporal density. Building upon these segments, we introduce three domain-specific indicators to capture abnormal stop behaviors. To further mitigate the impact of sparsity, we develop Locally Temporal-Indicator Guided Adjustment (LTIGA), which smooths these indicators via local similarity graphs. To overcome label scarcity, we construct a spatial-temporal graph where each segment is a node with LTIGA-refined features. We apply label propagation to expand weak supervision across the graph, followed by a GCN to learn relational patterns. A final self-training module incorporates high-confidence pseudo-labels to iteratively improve predictions. Experiments on real-world coach data show an AUC of 0.854 and AP of 0.866 using only 10 labeled instances, outperforming prior methods. The code and dataset are publicly available at \href{https://github.com/pangjunbiao/Abnormal-Stop-Detection-SSL.git}

Zero-Shot CFC: Fast Real-World Image Denoising based on Cross-Frequency Consistency

Zero-shot denoisers address the dataset dependency of deep-learning-based denoisers, enabling the denoising of unseen single images. Nonetheless, existing zero-shot methods suffer from long training times and rely on the assumption of noise independence and a zero-mean property, limiting their effectiveness in real-world denoising scenarios where noise characteristics are more complicated. This paper proposes an efficient and effective method for real-world denoising, the Zero-Shot denoiser based on Cross-Frequency Consistency (ZSCFC), which enables training and denoising with a single noisy image and does not rely on assumptions about noise distribution. Specifically, image textures exhibit position similarity and content consistency across different frequency bands, while noise does not. Based on this property, we developed cross-frequency consistency loss and an ultralight network to realize image denoising. Experiments on various real-world image datasets demonstrate that our ZSCFC outperforms other state-of-the-art zero-shot methods in terms of computational efficiency and denoising performance.

TerraCodec: Compressing Earth Observations

Earth observation (EO) satellites produce massive streams of multispectral image time series, posing pressing challenges for storage and transmission. Yet, learned EO compression remains fragmented, lacking publicly available pretrained models and misaligned with advances in compression for natural imagery. Image codecs overlook temporal redundancy, while video codecs rely on motion priors that fail to capture the radiometric evolution of largely static scenes. We introduce TerraCodec (TEC), a family of learned codecs tailored to EO. TEC includes efficient image-based variants adapted to multispectral inputs, as well as a Temporal Transformer model (TEC-TT) that leverages dependencies across time. To overcome the fixed-rate setting of today's neural codecs, we present Latent Repacking, a novel method for training flexible-rate transformer models that operate on varying rate-distortion settings. Trained on Sentinel-2 data, TerraCodec outperforms classical codecs, achieving 3-10x stronger compression at equivalent image quality. Beyond compression, TEC-TT enables zero-shot cloud inpainting, surpassing state-of-the-art methods on the AllClear benchmark. Our results establish bespoke, learned compression algorithms as a promising direction for Earth observation. Code and model weights will be released under a permissive license.

Towards Fast Coarse-graining and Equation Discovery with Foundation Inference Models

High-dimensional recordings of dynamical processes are often characterized by a much smaller set of effective variables, evolving on low-dimensional manifolds. Identifying these latent dynamics requires solving two intertwined problems: discovering appropriate coarse-grained variables and simultaneously fitting the governing equations. Most machine learning approaches tackle these tasks jointly by training autoencoders together with models that enforce dynamical consistency. We propose to decouple the two problems by leveraging the recently introduced Foundation Inference Models (FIMs). FIMs are pretrained models that estimate the infinitesimal generators of dynamical systems (e.g., the drift and diffusion of a stochastic differential equation) in zero-shot mode. By amortizing the inference of the dynamics through a FIM with frozen weights, and training only the encoder-decoder map, we define a simple, simulation-consistent loss that stabilizes representation learning. A proof of concept on a stochastic double-well system with semicircle diffusion, embedded into synthetic video data, illustrates the potential of this approach for fast and reusable coarse-graining pipelines.

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance

In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing methods primarily focus on either fine-tuning LLMs to generate recommendations or integrating LLM-based embeddings into downstream models. In this work, we follow the latter direction and propose \textbf{TextGCN}, which applies parameter-free graph convolution layers directly over LLM-based item-title embeddings, instead of learning ID-based embeddings as in traditional methods. By combining language semantics with graph message passing, this architecture achieves state-of-the-art zero-shot performance, significantly outperforming prior approaches. Furthermore, we introduce \textbf{TextGCN-MLP}, which extends TextGCN with a trainable multilayer perceptron trained using a contrastive loss, achieving state-of-the-art in-domain performance on recommendation benchmarks. However, the zero-shot performance of TextGCN-MLP remains lower than that of TextGCN, highlighting the trade-off between in-domain specialization and zero-shot generalization. We release our code on github at \href{https://github.com/ChernovAndrey/TFCE}{github.com/ChernovAndrey/TFCE}.