Latest Research
Open-Set Domain Adaptation for Semantic Segmentation
Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer the pixel-wise knowledge from the labeled source domain to the unlabeled target domain.
Near Optimal Decentralized Optimization with Compression and Momentum Tracking
Communication efficiency has garnered significant attention as it is considered the main bottleneck for large-scale decentralized Machine Learning applications in distributed and federated settings.
MCDS-VSS: Moving Camera Dynamic Scene Video Semantic Segmentation by Filtering with Self-Supervised Geometry and Motion
Autonomous systems, such as self-driving cars, rely on reliable semantic environment perception for decision making.
$\textit{S}^3$Gaussian: Self-Supervised Street Gaussians for Autonomous Driving
Photorealistic 3D reconstruction of street scenes is a critical technique for developing real-world simulators for autonomous driving.
Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
Specifically, by restructuring the training objectives -- removing the answer from outputs and concatenating the question with the rationale as input -- CasCoD's two-step learning process ensures that students focus on learning rationales without interference from the preset answers, thus improving reasoning generalizability.
DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild
Image quality assessment (IQA) plays a critical role in selecting high-quality images and guiding compression and enhancement methods in a series of applications.
One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models
To address this, we propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
Further analysis shows that EDIT can generate high-quality CoTs with more correct key reasoning steps.
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
We believe that the GenVideo dataset and the DeMamba module will significantly advance the field of AI-generated video detection.
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Extensive experiments on language and vision benchmarks show that SVFT recovers up to 96% of full fine-tuning performance while training only 0. 006 to 0. 25% of parameters, outperforming existing methods that only recover up to 85% performance using 0. 03 to 0. 8% of the trainable parameter budget.
