Related papers: Just Shift It: Test-Time Prototype Shifting for Ze…
Generalized Zero-Shot Learning (GZSL) aims to recognize new categories with auxiliary semantic information,e.g., category attributes. In this paper, we handle the critical issue of domain shift problem, i.e., confusion between seen and…
Vision-language models have showcased impressive zero-shot classification capabilities when equipped with suitable text prompts. Previous studies have shown the effectiveness of test-time prompt tuning; however, these methods typically…
Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention…
Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recently, prompt pretraining in large-scale dataset (e.g.,…
The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT)…
Test-Time Optimization enables models to adapt to new data during inference by updating parameters on-the-fly. Recent advances in Vision-Language Models (VLMs) have explored learning prompts at test time to improve performance in downstream…
Transition Matching (TM) is an emerging paradigm for generative modeling that generalizes diffusion and flow-matching models as well as continuous-state autoregressive models. TM, similar to previous paradigms, gradually transforms noise…
We present Seg-TTO, a novel framework for zero-shot, open-vocabulary semantic segmentation (OVSS), designed to excel in specialized domain tasks. While current open-vocabulary approaches show impressive performance on standard segmentation…
Zero-Shot Learning (ZSL) aims to classify a test instance from an unseen category based on the training instances from seen categories, in which the gap between seen categories and unseen categories is generally bridged via visual-semantic…
Test-time scaling (TTS) methods have proven highly effective for LLMs, yet their application to vision-language models (VLMs) remains relatively underexplored. Existing VLM TTS methods largely require open-weight model access or expensive…
Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, where tokens attend only to preceding context, prevents effective token classification when…
Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with unusual image properties. In this paper, we investigate…
Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot recognition by comparing image embeddings to text-derived class prototypes. However, under domain shift, they suffer from feature drift, class-prior mismatch, and severe…
Data augmentation is a crucial technique for improving model generalization and robustness, particularly in deep learning models where training data is limited. Although many augmentation methods have been developed for time series…
This work summarizes two ways to accomplish Time-Series (TS) tasks in today's Large Language Model (LLM) context: LLM-for-TS (model-centric) designs and trains a fundamental large model, or fine-tunes a pre-trained LLM for TS data;…
Vision-Language Models (VLMs) show promise as zero-shot goal-conditioned value functions, but their frozen pre-trained representations limit generalization and temporal reasoning. We introduce VITA, a zero-shot value function learning…
Recent progress in large pre-trained vision language models (VLMs) has reached state-of-the-art performance on several object detection benchmarks and boasts strong zero-shot capabilities, but for optimal performance on specific targets…
Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale datasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept…
Test-time adaptation with pre-trained vision-language models (VLMs) has attracted increasing attention for tackling the issue of distribution shift during the test phase. While prior methods have shown effectiveness in addressing…
Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…