2529 papers
This paper introduces OmniEarth, a comprehensive benchmark comprising 9,275 images and 44,210 verified instructions that evaluates Vision-Language Models across 28 geospatial tasks with a focus on perception, reasoning, and robustness, revealing significant performance gaps in current models for remote sensing applications.
The paper introduces MORE-R1, a novel Large Vision-Language Model that leverages a two-stage training process combining Supervised Fine-Tuning on automatically constructed stepwise reasoning data and Reinforcement Learning with Group Relative Policy Optimization to achieve state-of-the-art performance in Multimodal Object-Entity Relation Extraction.
PruneSID is a training-free, synergistic importance-diversity framework that significantly enhances Vision-Language Model efficiency by employing Principal Semantic Components Analysis and Intra-group Non-Maximum Suppression to achieve state-of-the-art accuracy with extreme token compression and faster prefilling speeds.
StyleVLA is a physics-informed Vision Language Action model built on Qwen3-VL-4B that generates diverse, kinematically feasible driving trajectories tailored to specific styles, significantly outperforming state-of-the-art proprietary models on domain-specific autonomous driving tasks.
This paper proposes a novel component-aware, self-refining framework that combines a Self-Attention-based Autoencoder, a Coordinate-Preserving Gated Fusion module, and a Spatially Adaptive Refinement Revisor to generate high-fidelity, semantically accurate photorealistic images from freehand sketches, significantly outperforming existing GAN and diffusion models across diverse facial and non-facial datasets.
This paper introduces Diagonal Distillation, an asymmetric autoregressive framework that leverages temporal context and implicit optical flow to enable high-fidelity, real-time streaming video generation with a 277.3x speedup while mitigating error accumulation and motion incoherence.
This paper reports on the synthesis and seeks feedback for the future evaluation of an Artefact Model for Regulatory Requirements Engineering (AM4RRE), aiming to bridge the gap between organizational regulatory processes and ad-hoc software development practices to achieve systematic, integrated compliance by design.
The paper proposes SurgFed, a language-guided multi-task federated learning framework that utilizes Language-guided Channel Selection and Language-guided Hyper Aggregation to overcome tissue and task diversity challenges, thereby improving surgical video segmentation and depth estimation across heterogeneous clinical environments.
This paper introduces EmbC-Test, a Retrieval-Augmented Generation (RAG) pipeline that leverages project-specific artifacts to ground large language models, enabling the automated generation of syntactically correct and runtime-valid embedded C tests that reduce testing time by up to 66% while producing 270 tests per hour.
This paper introduces a hybrid algebraic verification technique implemented in TalisMan2.0 that utilizes parallel multimodular reasoning to efficiently verify arithmetic circuits with large operands while avoiding the computational overhead of big integer arithmetic.
The paper presents Context-Nav, a training-free framework for text-goal instance navigation that combines caption-driven frontier ranking for global exploration with viewpoint-aware 3D spatial verification to accurately disambiguate target objects in cluttered environments, achieving state-of-the-art performance on InstanceNav and CoIN-Bench.
This paper investigates the reliability of Vision-Language Models (VLMs) in autonomous driving by exposing their tendencies toward response inconsistency and weak temporal reasoning, and subsequently proposes the FutureVQA benchmark and a self-supervised chain-of-thought tuning method to enhance grounded future scene reasoning without requiring temporal labels.
This paper introduces RuleSafe, a new long-horizon articulated manipulation benchmark featuring non-Markovian safe-unlocking tasks, and proposes VQ-Memory, a vector-quantized temporal representation that significantly enhances the planning, generalization, and efficiency of Vision-Language-Action models in complex robotic simulations.
The paper introduces RESBev, a plug-and-play framework that enhances the robustness of Bird's-eye-view (BEV) perception systems against sensor degradation and adversarial attacks by reframing the problem as latent semantic prediction to reconstruct clean features from corrupted observations.
This paper proposes DCAU-Net, a novel medical image segmentation framework that combines Differential Cross Attention to efficiently model long-range dependencies while reducing computational complexity, and a Channel-Spatial Feature Fusion strategy to adaptively integrate semantic and spatial details, thereby achieving enhanced segmentation accuracy and robustness.
This paper proposes a large language model-driven method for generating dynamic, semantically aligned speech and gestures for pedagogical agents in virtual reality, demonstrating through user experience experiments that such multimodal expressions significantly enhance learning effectiveness, engagement, and social presence while reducing fatigue and boredom.
This paper proposes a reinforcement learning-based post-training strategy that extends Group Relative Policy Optimization (GRPO) with hybrid and process-level rewards to enable existing unified vision-language models to generate high-quality multimodal interleaved outputs without relying on large-scale interleaved datasets.
This paper introduces DynHiL-EQA, a new dataset for dynamic human-in-the-loop Embodied Question Answering, and proposes DIVRR, a training-free framework that enhances robustness and inference efficiency by refining ambiguous views and selectively managing memory in dynamic environments.
This paper introduces NS-VLA, a novel Neuro-Symbolic Vision-Language-Action framework that integrates symbolic encoding, solving, and online reinforcement learning to achieve superior data efficiency, zero-shot generalizability, and expanded exploration in robotic manipulation compared to existing methods.
This paper presents a specialized, LLM-based Automated Program Repair framework designed to automatically secure cross-compartment interfaces in compartmentalized software by integrating a fuzzer, compartment-aware analysis techniques, and a validation component to address the limitations of existing general-purpose repair tools.