Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration

Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through empirical analysis, we identify a phenomenon termed Logit-Attention Divergence, in which output logits are heavily biased while internal attention maps remain well-aligned with relevant visual evidence. This observation reveals a fundamental limitation of existing logit-level calibration methods such as PriDe. Based on this insight, we propose a training-free, attention-guided debiasing framework that leverages intrinsic attention signals for instance-level correction at inference time, requiring only a minimal calibration set with negligible computational overhead. Experiments on MS-COCO-based benchmarks show that our method substantially improves permutation invariance and achieves state-of-the-art performance, enhancing accuracy by over 40\% compared to baselines. Code is available at https://github.com/brightXian/LAD.

TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection

Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods mainly rely on static negative labels constructed before inference, limiting their ability to cover diverse and evolving OOD concepts. Although test-time expansion provides a natural solution, naively learning negative semantics from potential OOD samples may introduce hard ID contamination. To address this issue, we propose a \textbf{T}est-time \textbf{I}D-prototype-separated \textbf{N}egative \textbf{S}emantics learning method, termed \textbf{TINS}. TINS learns sample-specific negative text embeddings via image-to-text modality inversion and introduces ID-prototype-separated regularization to keep them separated from ID semantics. To further stabilize negative semantics expansion, TINS employs group-wise aggregation scoring and a buffer update strategy. Extensive experiments across Four-OOD, OpenOOD, Temporal-shift, and Various ID settings show consistent improvements over strong baselines. Notably, on the Four-OOD benchmark with ImageNet-1K as ID, TINS reduces the average FPR95 from 14.04\% to 6.72\%. Our code is available at https://github.com/zxk1212/tins.

V-CAGE: Vision-Closed-Loop Agentic Generation Engine for Robotic Manipulation

Scaling Vision-Language-Action (VLA) models requires massive datasets that are both semantically coherent and physically feasible. However, existing scene generation methods often lack context-awareness, making it difficult to synthesize high-fidelity environments embedded with rich semantic information, frequently resulting in unreachable target positions that cause tasks to fail prematurely. We present V-CAGE (Vision-Closed-loop Agentic Generation Engine), an agentic framework for autonomous robotic data synthesis. Unlike traditional scripted pipelines, V-CAGE operates as an embodied agentic system, leveraging foundation models to bridge high-level semantic reasoning with low-level physical interaction. Specifically, we introduce Inpainting-Guided Scene Construction to systematically arrange context-aware layouts, ensuring that the generated scenes are both semantically structured and kinematically reachable. To ensure trajectory correctness, we integrate functional metadata with a Vision-Language Model based closed-loop verification mechanism, acting as a visual critic to rigorously filter out silent failures and sever the error propagation chain. Finally, to overcome the storage bottleneck of massive video datasets, we implement a perceptually-driven compression algorithm that achieves over 90\% filesize reduction without compromising downstream VLA training efficacy. By centralizing semantic layout planning and visual self-verification, V-CAGE automates the end-to-end pipeline, enabling the highly scalable synthesis of diverse, high-quality robotic manipulation datasets.

An End-to-end Flight Control Network for High-speed UAV Obstacle Avoidance based on Event-Depth Fusion

Achieving safe, high-speed autonomous flight in complex environments with static, dynamic, or mixed obstacles remains challenging, as a single perception modality is incomplete. Depth cameras are effective for static objects but suffer from motion blur at high speeds. Conversely, event cameras excel at capturing rapid motion but struggle to perceive static scenes. To exploit the complementary strengths of both sensors, we propose an end-to-end flight control network that achieves feature-level fusion of depth images and event data through a bidirectional crossattention module. The end-to-end network is trained via imitation learning, which relies on high-quality supervision. Building on this insight, we design an efficient expert planner using Spherical Principal Search (SPS). This planner reduces computational complexity from $O(n^2)$ to $O(n)$ while generating smoother trajectories, achieving over 80% success rate at 17m/s--nearly 20% higher than traditional planners. Simulation experiments show that our method attains a 70-80% success rate at 17 m/s across varied scenes, surpassing single-modality and unidirectional fusion models by 10-20%. These results demonstrate that bidirectional fusion effectively integrates event and depth information, enabling more reliable obstacle avoidance in complex environments with both static and dynamic objects.

Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning

Offline reinforcement learning (RL) optimizes policies from a previously collected static dataset and is an important branch of RL. A popular and promising approach is to regularize actor-critic methods with behavior cloning (BC), which yields realistic policies and mitigates bias from out-of-distribution actions, but can impose an often-overlooked performance ceiling: when dataset actions are suboptimal, indiscriminate imitation structurally prevents the actor from fully exploiting high-value regions suggested by the critic, especially in later training when imitation is already dominant. We formally analyzed this limitation by investigating convergence properties of BC-regularized actor-critic optimization and verified it on a controlled continuous bandit task. To break this ceiling, we propose proximal action replacement (PAR), a plug-and-play training sample replacer that progressively replaces low-value actions with high-value actions generated by a stable actor, broadening the action exploration space while reducing the impact of low-value data. PAR is compatible with multiple BC regularization paradigms. Extensive experiments across offline RL benchmarks show that PAR consistently improves performance and approaches state-of-the-art when combined with the basic TD3+BC.

V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks

Learning long-horizon embodied behaviors from synthetic data remains challenging because generated scenes are often physically implausible, language-driven programs frequently "succeed" without satisfying task semantics, and high-level instructions require grounding into executable action sequences. To address these limitations, we introduce V-CAGE, a closed-loop framework for generating robust, semantically aligned manipulation datasets at scale. First, we propose a context-aware instantiation mechanism that enforces geometric consistency during scene synthesis. By dynamically maintaining a map of prohibited spatial areas as objects are placed, our system prevents interpenetration and ensures reachable, conflict-free configurations in cluttered environments. Second, to bridge the gap between abstract intent and low-level control, we employ a hierarchical instruction decomposition module. This decomposes high-level goals (e.g., "get ready for work") into compositional action primitives, facilitating coherent long-horizon planning. Crucially, we enforce semantic correctness through a VLM-based verification loop. Acting as a visual critic, the VLM performs rigorous rejection sampling after each subtask, filtering out "silent failures" where code executes but fails to achieve the visual goal. Experiments demonstrate that V-CAGE yields datasets with superior physical and semantic fidelity, significantly boosting the success rate and generalization of downstream policies compared to non-verified baselines.

Learning Primitive Embodied World Models: Towards Scalable Robotic Learning

While video-generation-based embodied world models have gained increasing attention, their reliance on large-scale embodied interaction data remains a key bottleneck. The scarcity, difficulty of collection, and high dimensionality of embodied data fundamentally limit the alignment granularity between language and actions and exacerbate the challenge of long-horizon video generation--hindering generative models from achieving a "GPT moment" in the embodied domain. There is a naive observation: the diversity of embodied data far exceeds the relatively small space of possible primitive motions. Based on this insight, we propose a novel paradigm for world modeling--Primitive Embodied World Models (PEWM). By restricting video generation to fixed short horizons, our approach 1) enables fine-grained alignment between linguistic concepts and visual representations of robotic actions, 2) reduces learning complexity, 3) improves data efficiency in embodied data collection, and 4) decreases inference latency. By equipping with a modular Vision-Language Model (VLM) planner and a Start-Goal heatmap Guidance mechanism (SGG), PEWM further enables flexible closed-loop control and supports compositional generalization of primitive-level policies over extended, complex tasks. Our framework leverages the spatiotemporal vision priors in video models and the semantic awareness of VLMs to bridge the gap between fine-grained physical interaction and high-level reasoning, paving the way toward scalable, interpretable, and general-purpose embodied intelligence.

Bayesian Cross-Modal Alignment Learning for Few-Shot Out-of-Distribution Generalization

Recent advances in large pre-trained models showed promising results in few-shot learning. However, their generalization ability on two-dimensional Out-of-Distribution (OoD) data, i.e., correlation shift and diversity shift, has not been thoroughly investigated. Researches have shown that even with a significant amount of training data, few methods can achieve better performance than the standard empirical risk minimization method (ERM) in OoD generalization. This few-shot OoD generalization dilemma emerges as a challenging direction in deep neural network generalization research, where the performance suffers from overfitting on few-shot examples and OoD generalization errors. In this paper, leveraging a broader supervision source, we explore a novel Bayesian cross-modal image-text alignment learning method (Bayes-CAL) to address this issue. Specifically, the model is designed as only text representations are fine-tuned via a Bayesian modelling approach with gradient orthogonalization loss and invariant risk minimization (IRM) loss. The Bayesian approach is essentially introduced to avoid overfitting the base classes observed during training and improve generalization to broader unseen classes. The dedicated loss is introduced to achieve better image-text alignment by disentangling the causal and non-casual parts of image features. Numerical experiments demonstrate that Bayes-CAL achieved state-of-the-art OoD generalization performances on two-dimensional distribution shifts. Moreover, compared with CLIP-like models, Bayes-CAL yields more stable generalization performances on unseen classes. Our code is available at https://github.com/LinLLLL/BayesCAL.

InfoBound: A Provable Information-Bounds Inspired Framework for Both OoD Generalization and OoD Detection

In real-world scenarios, distribution shifts give rise to the importance of two problems: out-of-distribution (OoD) generalization, which focuses on models' generalization ability against covariate shifts (i.e., the changes of environments), and OoD detection, which aims to be aware of semantic shifts (i.e., test-time unseen classes). Real-world testing environments often involve a combination of both covariate and semantic shifts. While numerous methods have been proposed to address these critical issues, only a few works tackled them simultaneously. Moreover, prior works often improve one problem but sacrifice the other. To overcome these limitations, we delve into boosting OoD detection and OoD generalization from the perspective of information theory, which can be easily applied to existing models and different tasks. Building upon the theoretical bounds for mutual information and conditional entropy, we provide a unified approach, composed of Mutual Information Minimization (MI-Min) and Conditional Entropy Maximizing (CE-Max). Extensive experiments and comprehensive evaluations on multi-label image classification and object detection have demonstrated the superiority of our method. It successfully mitigates trade-offs between the two challenges compared to competitive baselines.

Decision SpikeFormer: Spike-Driven Transformer for Decision Making

Offline reinforcement learning (RL) enables policy training solely on pre-collected data, avoiding direct environment interaction - a crucial benefit for energy-constrained embodied AI applications. Although Artificial Neural Networks (ANN)-based methods perform well in offline RL, their high computational and energy demands motivate exploration of more efficient alternatives. Spiking Neural Networks (SNNs) show promise for such tasks, given their low power consumption. In this work, we introduce DSFormer, the first spike-driven transformer model designed to tackle offline RL via sequence modeling. Unlike existing SNN transformers focused on spatial dimensions for vision tasks, we develop Temporal Spiking Self-Attention (TSSA) and Positional Spiking Self-Attention (PSSA) in DSFormer to capture the temporal and positional dependencies essential for sequence modeling in RL. Additionally, we propose Progressive Threshold-dependent Batch Normalization (PTBN), which combines the benefits of LayerNorm and BatchNorm to preserve temporal dependencies while maintaining the spiking nature of SNNs. Comprehensive results in the D4RL benchmark show DSFormer's superiority over both SNN and ANN counterparts, achieving 78.4% energy savings, highlighting DSFormer's advantages not only in energy efficiency but also in competitive performance. Code and models are public at https://wei-nijuan.github.io/DecisionSpikeFormer.