From the 1 of 4 linked papers with an AI index.
4 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
The paper introduces LEEPS, a latent-guided explore‑exploit prompt sampler that selects prompts before rollout to reduce wasted generation budget and improve reinforcement learning…
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…