5 papers
Local Margin Restoration for Test-Time Adaptation of Vision-Language Models
Yan Huang, Guowei Wang, Xu Wang +2
Vision-language models (VLMs) such as CLIP exhibit remarkable zero-shot capabilities, yet their performance frequently degrades sharply under unexpected test-time distribution shif…
LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models
Shuang Liang, Haoyang Zhou, Yifan Gong +2
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generat…
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
Haoyang Zhou, Li Kong, Shijie Ren +4
Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing token…
Effortless Active Labeling for Long-Term Test-Time Adaptation
Guowei Wang, Changxing Ding
Long-term test-time adaptation (TTA) is a challenging task due to error accumulation. Recent approaches tackle this issue by actively labeling a small proportion of samples in each…
Decoupled Prototype Learning for Reliable Test-Time Adaptation
Guowei Wang, Changxing Ding, Wentao Tan +1
Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with…