AI
Training-Free VLM Personalization via Calibrated Residual Decoding
Researchers have proposed a method to personalize vision-language models without retraining them. Th...
AI
GAN-Diff : Coupling Pretrained WGAN-GP Features with Conditional Diffusion U-Nets
Researchers have developed a hybrid framework that combines the strengths of generative adversarial ...
AI
Multi-Task Learning for Non-Canonical Phoneme Recognition via Articulatory Feature Decomposition
Researchers have developed a new approach to phoneme recognition that can handle non-canonical speec...
AI
Length-Adaptive Decoding for Masked Diffusion Machine Translation
Researchers have proposed a new method for improving machine translation called Entropy-Valley (EV)....
AI
OVIBench: Benchmarking Online Video Question Answering under Interruption
Researchers have developed a new benchmark called OVIBench to evaluate how well ...
AI
Learning from the Test: Self-Referential Differential Testing for Deep RL Agents
Researchers have proposed a new framework called Delta for evaluating and improv...
AI
LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model
Researchers have developed an evaluation framework to predict how large language...
AI
The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction
Researchers have created a benchmark called The Imitator Game to test how well r...