8949 papers
This paper introduces Pluggable Pruning with Contiguous Layer Distillation (PPCL), a flexible framework that reduces Diffusion Transformer parameters by 50% with minimal performance loss through redundant layer identification and a plug-and-play alternating distillation scheme, enabling efficient deployment in resource-constrained environments.
This paper introduces Visual Preference Policy Optimization (ViPO), a lightweight and architecture-agnostic variant of Group Relative Policy Optimization that enhances visual generation by replacing coarse scalar rewards with structured, pixel-level advantage maps to better align models with human preferences and correct localized artifacts.
This paper introduces KeyTailor, a novel framework featuring a keyframe-driven details injection strategy to enhance garment dynamics and background integrity in video virtual try-on without increasing architectural complexity, accompanied by the large-scale ViT-HD dataset to address data limitations.
CogFlow is a novel three-stage framework that enhances visual mathematical problem solving by introducing a knowledge internalization stage and specialized reward mechanisms to ensure extracted visual cues are faithfully integrated into reasoning, supported by a new high-quality dataset called MathCog.
Fast-ThinkAct is an efficient Vision-Language-Action framework that utilizes preference-guided distillation of verbalizable latent reasoning to significantly reduce inference latency while maintaining strong performance in long-horizon planning, few-shot adaptation, and failure recovery.
This paper introduces MetamerGen, a dual-stream latent diffusion model that generates perceptually aligned image metamers by fusing peripheral scene gist with high-resolution fixation details, thereby validating its ability to reconstruct human scene understanding through behavioral experiments.
This paper proposes a principal component analysis-based self-supervised deep neural network (THz-SSDD) that effectively addresses the simultaneous challenges of low-frequency blurring and high-frequency noise in terahertz amplitude images by leveraging a Recorrupted-to-Recorrupted learning strategy and PCA reconstruction without requiring labeled data.
This paper addresses the fragmentation of pre-computed Geospatial Foundation Model embeddings by proposing a three-layer taxonomy and extending TorchGeo with a unified API to standardize access, thereby enabling interoperable, reproducible, and accessible Earth observation workflows.
This paper proposes ACLNet, an Affinity Contrastive Learning Network that enhances skeleton-based human activity understanding by leveraging structural inter-class similarities to form activity superclasses and employing a dynamic temperature schedule with margin-based contrastive strategies to improve feature discrimination across multiple benchmarks.
This paper introduces CER-HV, a human-in-the-loop framework that effectively identifies and cleans label errors in Arabic-script handwritten text recognition datasets, thereby revealing significant data quality issues and improving recognition performance across multiple languages.
This paper proposes a Pareto-guided optimization framework for medical image segmentation that employs a region-wise curriculum strategy and a fuzzy labeling mechanism to prioritize learning from certain regions, thereby stabilizing gradients and guiding the model toward Pareto-optimal solutions that outperform traditional methods in handling boundary ambiguity.
The paper proposes DVLA-RL, a novel few-shot learning framework that leverages reinforcement learning gating to dynamically integrate progressive dual-level vision-language alignments—ranging from fine-grained attributes to holistic descriptions generated by large language models—thereby achieving state-of-the-art performance across diverse benchmarks.
This paper proposes a novel all-optical computing framework using diffractive neural networks to perform energy-efficient, real-time semantic segmentation and lane detection for autonomous driving, demonstrating its effectiveness on the CityScapes dataset and in diverse simulated driving scenarios.
GOT-Edit introduces an online cross-modality model editing framework that integrates 3D geometric cues into generic object tracking by leveraging a pre-trained Visual Geometry Grounded Transformer and null-space constraints, thereby significantly enhancing robustness against occlusion and distractors while preserving semantic discrimination.
The paper introduces UI-Venus-1.5, a unified end-to-end GUI agent family featuring 2B, 8B, and 30B-A3B variants that leverage mid-training, online reinforcement learning, and model merging to achieve state-of-the-art performance on diverse benchmarks and robust real-world navigation across Chinese mobile apps.
This study systematically evaluates geospatial foundation models (Prithvi-EO-2.0 and TerraMind) for ecological mapping, demonstrating their consistent superiority over traditional baselines across forest trait estimation, land cover mapping, and peatland detection while highlighting the critical importance of dataset alignment and high-resolution inputs for optimal performance.
DriveMamba proposes a task-centric, scalable state space model for efficient end-to-end autonomous driving that replaces the sequential Transformer-based paradigm with a unified Mamba decoder featuring linear-complexity operators and bidirectional trajectory-guided scanning to overcome information loss, cumulative errors, and computational inefficiencies in handling spatiotemporal inputs.
Sim2Radar is an end-to-end framework that bridges the radar sim-to-real gap by synthesizing physics-based mmWave data from single-view RGB images using VLM-guided material inference, thereby significantly improving downstream 3D radar perception through transfer learning.
This paper introduces HERO, a novel paradigm for humanoid robots that combines large vision models for open-vocabulary scene understanding with a residual-aware end-effector tracking policy trained in simulation, enabling robust and generalizable visual loco-manipulation of diverse objects in real-world environments.
This study presents the first 10m-resolution tree crop map for South America, revealing that existing regulatory definitions often misclassify established smallholder agroforestry as forest, thereby highlighting the need for high-resolution data to ensure equitable and effective zero-deforestation policies.